Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 25068
    Prev
    Next
    INDEX
    Explanations

    Domains and "EA"

    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
    אתגר
    -0.07
    ▆
    -0.07
    桷
    -0.07
     playerName
    -0.07
    깽
    -0.07
    Clause
    -0.07
    像个
    -0.07
    .isDebugEnabled
    -0.07
    Î
    -0.07
    atom
    -0.07
    POSITIVE LOGITS
    фи
    0.07
     vitamins
    0.07
    ']]);↵
    0.07
     bitte
    0.07
    VPN
    0.07
     س
    0.06
    战友
    0.06
     breathable
    0.06
     metaph
    0.06
     Levi
    0.06
    Activations Density 0.099%

    No Known Activations