Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 48718
    Prev
    Next
    INDEX
    Explanations

    Reviews/opinions

    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
     /
    -0.08
    推出的
    -0.07
    ToStr
    -0.07
     setValue
    -0.07
    ,则
    -0.07
    ▪
    -0.07
     attorneys
    -0.07
    _produk
    -0.07
    both
    -0.07
    ']))
    ↵
    -0.07
    POSITIVE LOGITS
     manifestation
    0.07
     Nested
    0.07
     огр
    0.07
    COORD
    0.06
     어
    0.06
     prominently
    0.06
     LAND
    0.06
    _APPEND
    0.06
    웢
    0.06
    Ҝ
    0.06
    Activations Density 0.099%

    No Known Activations