© 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. 129379
    Prev
    Next
    INDEX
    Explanations

    nav

    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
     lure
    -0.08
    씨
    -0.07
     Giles
    -0.07
    -----
    -0.07
    ide
    -0.07
     trap
    -0.07
     curator
    -0.07
    	Color
    -0.07
     Sorry
    -0.07
     DEBUG
    -0.07
    POSITIVE LOGITS
    @FXML
    0.07
    孜
    0.07
    を目指
    0.07
    坚实的
    0.07
    받
    0.07
    每个月
    0.07
     MatButtonModule
    0.07
    (reordered
    0.06
    MED
    0.06
    working
    0.06
    Activations Density 0.000%

    No Known Activations