© 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. 62307
    Prev
    Next
    INDEX
    Explanations

    stream/downstream

    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
    湟
    -0.07
    愉快
    -0.07
    ₑ
    -0.07
     Fayette
    -0.07
    愉
    -0.07
     Lopez
    -0.07
     isEqual
    -0.06
    茫
    -0.06
     мас
    -0.06
     müşter
    -0.06
    POSITIVE LOGITS
    _generic
    0.08
    하게
    0.08
    Companies
    0.07
     Conversation
    0.07
     advice
    0.07
    Reminder
    0.07
    cover
    0.07
     Автор
    0.07
    椁
    0.07
    ספו
    0.07
    Activations Density 0.007%

    No Known Activations