© 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. 71049
    Prev
    Next
    INDEX
    Explanations

    colons

    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
     Mach
    -0.07
     Babies
    -0.07
    olu
    -0.07
     Come
    -0.07
    逋
    -0.07
     Wouldn
    -0.07
     And
    -0.07
    xce
    -0.07
    lington
    -0.07
     Lyn
    -0.07
    POSITIVE LOGITS
     tabel
    0.07
     שק
    0.07
     FileNotFoundException
    0.07
    LING
    0.07
    键盘
    0.07
    Wildcard
    0.07
    뱉
    0.07
    .Forms
    0.06
     لك
    0.06
    ᠮ
    0.06
    Activations Density 0.007%

    No Known Activations