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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 49866
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    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
    的动力
    -0.07
    	Element
    -0.07
    	Button
    -0.07
     منتخب
    -0.07
    ervention
    -0.07
     station
    -0.07
     Repos
    -0.07
     transitional
    -0.07
    安心
    -0.07
     intersection
    -0.06
    POSITIVE LOGITS
    Fetch
    0.08
    ể
    0.07
     Tips
    0.07
    떻
    0.07
     bru
    0.07
     harmless
    0.07
    äl
    0.06
     сли
    0.06
    _tm
    0.06
    ъ
    0.06
    Activations Density 0.105%

    No Known Activations