© 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. 48964
    Prev
    Next
    INDEX
    Explanations

    Phase 1 clinical trials

    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
     isAuthenticated
    -0.07
    אס
    -0.07
    	sort
    -0.07
     أمر
    -0.07
    .Fill
    -0.07
    蓄
    -0.06
    汁
    -0.06
    ックス
    -0.06
    就不
    -0.06
    Am
    -0.06
    POSITIVE LOGITS
    观看
    0.08
     donn
    0.08
     этот
    0.08
     pivot
    0.07
    cepts
    0.07
     prima
    0.07
    +(\
    0.07
    computer
    0.07
     NSW
    0.07
    מו
    0.07
    Activations Density 0.064%

    No Known Activations