© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 34971
    Prev
    Next
    INDEX
    Explanations

    science fiction

    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
    主要包括
    -0.07
     organizations
    -0.07
     исп
    -0.07
     לראש
    -0.07
     Appalachian
    -0.07
    吳
    -0.06
    積極
    -0.06
    	setup
    -0.06
     Mike
    -0.06
     concurrent
    -0.06
    POSITIVE LOGITS
    чная
    0.08
    pta
    0.07
    ntax
    0.07
    afia
    0.07
    𝘆
    0.07
    _figure
    0.07
    分彩
    0.07
    ntl
    0.07
    bonus
    0.07
    퇘
    0.06
    Activations Density 0.017%

    No Known Activations