© 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. 61358
    Prev
    Next
    INDEX
    Explanations

    warning

    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
    胀
    -0.08
    アルバム
    -0.08
    面向
    -0.07
    ൾ
    -0.07
    gment
    -0.07
    CUSTOM
    -0.07
     loyalty
    -0.07
    legg
    -0.07
    合法
    -0.07
    众多
    -0.07
    POSITIVE LOGITS
    ömür
    0.08
     uses
    0.07
    מועצה
    0.07
    جم
    0.07
    揍
    0.06
    Fire
    0.06
    됍
    0.06
     eskorte
    0.06
     overrun
    0.06
     '.'
    0.06
    Activations Density 0.025%

    No Known Activations