Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 88338
    Prev
    Next
    INDEX
    Explanations

    say punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .defer
    -0.08
     Phaser
    -0.08
     Typeface
    -0.07
     Beacon
    -0.07
     anxious
    -0.07
    .acquire
    -0.07
    𝓷
    -0.07
     Whoever
    -0.06
     prostituerade
    -0.06
    transparent
    -0.06
    POSITIVE LOGITS
     בה
    0.07
     ↵    ↵
    0.07
    .'↵↵
    0.07
    当晚
    0.07
    各县
    0.07
    已是
    0.07
    ()")↵
    0.07
    	dd
    0.07
    顧
    0.07
    的に
    0.07
    Activations Density 0.850%

    No Known Activations