© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 11220
    Prev
    Next
    INDEX
    Explanations

    legal/financial documents

    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
    /provider
    -0.07
    Ki
    -0.07
    InParameter
    -0.07
    mnt
    -0.07
     davon
    -0.07
    _owned
    -0.07
    ips
    -0.07
    lim
    -0.06
    学前
    -0.06
    戎
    -0.06
    POSITIVE LOGITS
    金属
    0.08
     реак
    0.07
    ﰼ
    0.07
     intense
    0.07
    _OFFSET
    0.07
    Vertex
    0.07
     altri
    0.07
     Socket
    0.07
    的精神
    0.07
     получен
    0.07
    Activations Density 0.035%

    No Known Activations