© 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. 7-RESID-POST-AA
    6. 9160
    Prev
    Next
    INDEX
    Explanations

    study

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ottie
    -0.09
    afort
    -0.08
     ====
    -0.08
    该游戏
    -0.08
     MSM
    -0.08
    .fp
    -0.08
     shipment
    -0.07
     Warranty
    -0.07
    צעירים
    -0.07
    icens
    -0.07
    POSITIVE LOGITS
     zeros
    0.07
     stellar
    0.06
     bits
    0.06
    previous
    0.06
    '(
    0.06
    ᇂ
    0.06
    èles
    0.06
     stars
    0.06
    数额
    0.06
    隺
    0.06
    Activations Density 0.018%

    No Known Activations