© 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. 84955
    Prev
    Next
    INDEX
    Explanations

    ui

    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
     '..
    -0.07
     אכן
    -0.07
     kcal
    -0.06
     caut
    -0.06
     obr
    -0.06
    ǭ
    -0.06
    ignite
    -0.06
     rond
    -0.06
     fot
    -0.06
    struk
    -0.06
    POSITIVE LOGITS
    artial
    0.07
    	token
    0.07
    inner
    0.07
    见到
    0.07
     точки
    0.07
    咱们
    0.07
     créer
    0.07
    _zip
    0.07
    cached
    0.07
    _Request
    0.06
    Activations Density 0.003%

    No Known Activations