© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 74713
    Prev
    Next
    INDEX
    Explanations

    Hen

    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
    _PB
    -0.07
    任职
    -0.07
     upright
    -0.07
     vibrations
    -0.07
    Pos
    -0.07
    落ち
    -0.07
    ']}
    -0.07
     deviations
    -0.07
    に入る
    -0.07
    無し�
    -0.07
    POSITIVE LOGITS
     dific
    0.07
     acknow
    0.07
    ическую
    0.07
     strongest
    0.07
     xnxx
    0.07
     الفند
    0.07
    prene
    0.06
     GameManager
    0.06
    刎
    0.06
    >,</
    0.06
    Activations Density 0.006%

    No Known Activations