© 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. 25774
    Prev
    Next
    INDEX
    Explanations

    rhythm

    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
    匐
    -0.07
    俯
    -0.07
     encuent
    -0.07
    تون
    -0.07
    的话语
    -0.07
     Pip
    -0.07
    ﾟ
    -0.07
    بحث
    -0.07
    ằng
    -0.07
    ǜ
    -0.06
    POSITIVE LOGITS
    챈
    0.08
    Numero
    0.07
    Retail
    0.07
    汞
    0.07
    ᗷ
    0.07
     Pregnancy
    0.07
    앤
    0.07
    �
    0.07
     radical
    0.07
    .setItems
    0.07
    Activations Density 0.008%

    No Known Activations