© 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. 11-RESID-POST-AA
    11. 29802
    Prev
    Next
    INDEX
    Explanations

    focus

    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
     vary
    -0.07
     preference
    -0.07
    的地位
    -0.07
    .layers
    -0.07
    Priv
    -0.07
     indices
    -0.06
     licensors
    -0.06
     sights
    -0.06
     anticipation
    -0.06
    ashes
    -0.06
    POSITIVE LOGITS
     chạm
    0.07
     noct
    0.07
    ��
    0.07
     où
    0.07
    Obama
    0.07
     wreak
    0.07
    徕
    0.07
    :)];↵
    0.07
     Klopp
    0.07
     Swan
    0.07
    Activations Density 0.026%

    No Known Activations