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. 11-RESID-POST-AA
    6. 1776
    Prev
    Next
    INDEX
    Explanations

    fs

    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
    委组织部
    -0.07
    _LOOKUP
    -0.07
     isValid
    -0.07
    inflate
    -0.07
     Lon
    -0.07
    options
    -0.07
    	MD
    -0.07
     Nes
    -0.07
     StringTokenizer
    -0.06
    David
    -0.06
    POSITIVE LOGITS
    使
    0.07
     compagn
    0.07
     greater
    0.06
    맻
    0.06
     מספר
    0.06
    檢查
    0.06
     menjadi
    0.06
    य
    0.06
    KN
    0.06
    今
    0.06
    Activations Density 0.002%

    No Known Activations