© 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. 11-RESID-POST-AA
    6. 30508
    Prev
    Next
    INDEX
    Explanations

    Autobiographical/self-referential

    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
    经销商
    -0.07
    »,
    -0.07
    .…
    -0.07
    主角
    -0.07
    有效
    -0.07
    كهرباء
    -0.07
     ==>
    -0.07
    ThemeProvider
    -0.07
     Pearson
    -0.07
    良好的
    -0.06
    POSITIVE LOGITS
    captures
    0.07
    먀
    0.07
    .cards
    0.07
    体制机制
    0.07
    _proto
    0.07
    ça
    0.07
    _constraint
    0.07
    XmlElement
    0.06
    _train
    0.06
    _car
    0.06
    Activations Density 0.101%

    No Known Activations