© 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
    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. 27175
    Prev
    Next
    INDEX
    Explanations

    product reviews

    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
    айд
    -0.07
    received
    -0.07
    wrapped
    -0.07
     Wooden
    -0.07
    曹操
    -0.07
    .photos
    -0.07
    .account
    -0.07
     police
    -0.07
    ethereum
    -0.07
    Allow
    -0.07
    POSITIVE LOGITS
    大力推进
    0.08
    衰退
    0.07
    妥善
    0.07
     дв
    0.07
    مفا
    0.06
    зна
    0.06
    席卷
    0.06
    球星
    0.06
    ומה
    0.06
    letters
    0.06
    Activations Density 0.042%

    No Known Activations