© 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. 121271
    Prev
    Next
    INDEX
    Explanations

    transcription

    np_max-act · gemini-2.0-flash
    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
    셥
    -0.07
    _OPTIONS
    -0.07
    低于
    -0.07
    훨
    -0.07
    棪
    -0.07
    �
    -0.07
    with
    -0.06
     approached
    -0.06
    ursions
    -0.06
    כנע
    -0.06
    POSITIVE LOGITS
     كما
    0.07
     Amazon
    0.07
    /******/
    0.07
     ręk
    0.07
     preserved
    0.07
    Ê
    0.07
     DOM
    0.07
    verified
    0.07
     inserted
    0.07
     indexing
    0.07
    Activations Density 0.017%

    No Known Activations