© 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. 62314
    Prev
    Next
    INDEX
    Explanations

    scientific records/citations

    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
    FileNotFoundException
    -0.08
     dönemde
    -0.07
    ,readonly
    -0.07
     "}\
    -0.07
    ཁ
    -0.07
    ユ
    -0.07
     medicines
    -0.07
    懊
    -0.07
    ﺤ
    -0.07
    isValid
    -0.07
    POSITIVE LOGITS
     dove
    0.07
     Samurai
    0.07
     League
    0.07
    жу
    0.07
    带着
    0.06
    рыв
    0.06
    鍪
    0.06
    SPEC
    0.06
    -label
    0.06
    一边
    0.06
    Activations Density 0.001%

    No Known Activations