© 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. 70213
    Prev
    Next
    INDEX
    Explanations

    around the

    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
    ESP
    -0.08
    排放
    -0.07
    ServletResponse
    -0.07
    一切都是
    -0.07
    Emp
    -0.07
    比利时
    -0.07
    镇
    -0.07
    옅
    -0.07
    铛
    -0.07
    踏上
    -0.07
    POSITIVE LOGITS
     vacuum
    0.08
    뮘
    0.07
    保温
    0.07
     Asian
    0.07
    san
    0.07
     rehabilitation
    0.06
    ㇰ
    0.06
    AsyncResult
    0.06
    cms
    0.06
    _FRAGMENT
    0.06
    Activations Density 0.071%

    No Known Activations