© 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. 30607
    Prev
    Next
    INDEX
    Explanations

    legal filings deadlines

    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
     KeyCode
    -0.07
    .add
    -0.07
    hz
    -0.07
    See
    -0.07
     Solver
    -0.06
     matriz
    -0.06
     Failed
    -0.06
     Hashtable
    -0.06
    ائن
    -0.06
    硬化
    -0.06
    POSITIVE LOGITS
    𝑴
    0.07
    𝑭
    0.07
    ｴ
    0.07
    <O
    0.07
    ическом
    0.07
    INGTON
    0.07
    -h
    0.06
    SHIP
    0.06
     buffering
    0.06
     Berkshire
    0.06
    Activations Density 0.054%

    No Known Activations