© 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. 15-RESID-POST-AA
    6. 84765
    Prev
    Next
    INDEX
    Explanations

    Java code

    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
     avi
    -0.07
    elpers
    -0.07
    本身就
    -0.07
     הע
    -0.07
     touring
    -0.07
     cheaper
    -0.06
    avin
    -0.06
     forensic
    -0.06
     Discount
    -0.06
    个国家
    -0.06
    POSITIVE LOGITS
     książki
    0.07
     fuzzy
    0.07
    ��索
    0.07
     paź
    0.07
    שוק
    0.07
     miệ
    0.07
     Nixon
    0.06
    Prompt
    0.06
     Bonnie
    0.06
    FREE
    0.06
    Activations Density 0.019%

    No Known Activations