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. 15-RESID-POST-AA
    6. 45924
    Prev
    Next
    INDEX
    Explanations

    Hajj pilgrimage

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tur
    -0.07
     Nhà
    -0.07
     proyecto
    -0.06
    בית
    -0.06
    𐤓
    -0.06
     COLUMN
    -0.06
    _TRANSACTION
    -0.06
    :view
    -0.06
    getto
    -0.06
    êt
    -0.06
    POSITIVE LOGITS
    _mean
    0.08
    _MIN
    0.07
     harassment
    0.07
    精神
    0.07
     keyboards
    0.07
    ราม
    0.07
    個人
    0.06
    ⊧
    0.06
    استفادة
    0.06
     raining
    0.06
    Activations Density 0.003%

    No Known Activations