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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RESID-POST-AA
    11. 1119
    Prev
    Next
    INDEX
    Explanations

    Advanced math

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Swap
    -0.07
     vex
    -0.07
    扭
    -0.07
     terr
    -0.06
    投机
    -0.06
    _PRE
    -0.06
    ENC
    -0.06
    _tolerance
    -0.06
    埭
    -0.06
     rad
    -0.06
    POSITIVE LOGITS
     álbum
    0.09
     число
    0.08
     ניתן
    0.07
    _special
    0.07
    /ui
    0.07
    ArgumentNullException
    0.07
    ografia
    0.07
    音樂
    0.07
     psychiatric
    0.07
    座谈会上
    0.07
    Activations Density 0.012%

    No Known Activations