© 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. 2289
    Prev
    Next
    INDEX
    Explanations

    each

    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
    hv
    -0.07
     Brass
    -0.07
     найд
    -0.07
    罾
    -0.07
    mongodb
    -0.07
     pull
    -0.07
    ripp
    -0.07
    Joseph
    -0.07
     is
    -0.07
    有些
    -0.07
    POSITIVE LOGITS
    太极
    0.07
    읶
    0.07
     ------------------------------------------------------------
    0.07
    盘活
    0.07
     catering
    0.07
    .inventory
    0.06
    _TIMESTAMP
    0.06
     ailments
    0.06
    峙
    0.06
    _paper
    0.06
    Activations Density 0.026%

    No Known Activations