© 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. 11-RESID-POST-AA
    11. 87587
    Prev
    Next
    INDEX
    Explanations

    protein

    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
     Relatives
    -0.08
     chairs
    -0.07
     futuristic
    -0.07
     personalize
    -0.07
     pancakes
    -0.07
     Bodies
    -0.07
     personalised
    -0.07
     calendars
    -0.07
    +=(
    -0.06
     rulers
    -0.06
    POSITIVE LOGITS
     легко
    0.07
     treating
    0.07
    供养
    0.07
    得天独
    0.07
    人才
    0.07
     INT
    0.06
    
    0.06
     بواسطة
    0.06
    农民
    0.06
    报考
    0.06
    Activations Density 0.011%

    No Known Activations