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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19-RESID-POST-AA
    6. 89416
    Prev
    Next
    INDEX
    Explanations

    Solution

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISTICS
    -0.07
    aph
    -0.07
    mand
    -0.07
    Ǐ
    -0.06
     jsonify
    -0.06
     دائم
    -0.06
     dinheiro
    -0.06
    ឥ
    -0.06
    的房子
    -0.06
    ()+
    -0.06
    POSITIVE LOGITS
     Recru
    0.07
    measure
    0.07
    Tracking
    0.07
     M
    0.07
    %M
    0.07
     Hunts
    0.06
    📦
    0.06
    writers
    0.06
    课题
    0.06
    Ge
    0.06
    Activations Density 0.000%

    No Known Activations