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. 19-RESID-POST-AA
    6. 88372
    Prev
    Next
    INDEX
    Explanations

    is

    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
    Surv
    -0.07
     реакци
    -0.07
    쟤
    -0.07
    tuple
    -0.06
    枝
    -0.06
    几乎所有
    -0.06
     Перв
    -0.06
     accused
    -0.06
    .jav
    -0.06
    自来水
    -0.06
    POSITIVE LOGITS
    Honda
    0.08
    롸
    0.07
     JSBracketAccess
    0.07
    工作经验
    0.07
     שת
    0.07
    /dialog
    0.07
    宏大
    0.07
    评测
    0.07
    ยา
    0.07
    会长
    0.07
    Activations Density 0.003%

    No Known Activations