© 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. 50018
    Prev
    Next
    INDEX
    Explanations

    ch

    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
    lead
    -0.08
     restrict
    -0.07
    死亡
    -0.07
    处于
    -0.07
    rich
    -0.07
    时表示
    -0.07
     Detective
    -0.07
     rogue
    -0.07
     expl
    -0.07
     suggests
    -0.07
    POSITIVE LOGITS
    Indexed
    0.07
     comentario
    0.07
    defs
    0.07
    INI
    0.06
    _analysis
    0.06
    Raise
    0.06
    serialized
    0.06
     Lowell
    0.06
     ámb
    0.06
    夔
    0.06
    Activations Density 0.002%

    No Known Activations