© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 8529
    Prev
    Next
    INDEX
    Explanations

    academic papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    这话
    -0.08
     nguyên
    -0.07
     Hotel
    -0.07
    persons
    -0.07
     Recipe
    -0.07
    منهج
    -0.06
     SIDE
    -0.06
     Defendants
    -0.06
     SON
    -0.06
     toe
    -0.06
    POSITIVE LOGITS
    eroon
    0.07
    口碑
    0.07
     встреча
    0.06
     współprac
    0.06
    .getUserId
    0.06
     surround
    0.06
    Boost
    0.06
     imaginary
    0.06
     Herrera
    0.06
     Aust
    0.06
    Activations Density 0.156%

    No Known Activations