© 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. 61418
    Prev
    Next
    INDEX
    Explanations

    protected

    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
     dah
    -0.07
    .MM
    -0.07
     hol
    -0.06
     eclectic
    -0.06
     ner
    -0.06
    第三届
    -0.06
    让消费者
    -0.06
    宸
    -0.06
    לילה
    -0.06
    江东
    -0.06
    POSITIVE LOGITS
    我还
    0.07
    经济
    0.07
     trait
    0.07
    胂
    0.07
    sharp
    0.07
     undef
    0.07
    警方
    0.07
    Chunk
    0.07
    ervoir
    0.07
    vironments
    0.07
    Activations Density 0.004%

    No Known Activations