© 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. 15-RESID-POST-AA
    11. 72790
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     completed
    -0.09
    ITO
    -0.07
     noticed
    -0.07
    لق
    -0.07
    OSC
    -0.07
     placed
    -0.07
    策
    -0.07
    estr
    -0.07
     portals
    -0.06
     nei
    -0.06
    POSITIVE LOGITS
     accumulation
    0.08
    种族
    0.07
    根源
    0.07
    )*(
    0.07
    รส
    0.07
     Grave
    0.07
    邮政
    0.07
    .Scale
    0.07
     inconvenient
    0.07
    ">(
    0.07
    Activations Density 0.243%

    No Known Activations