© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 85920
    Prev
    Next
    INDEX
    Explanations

    fetal stress test

    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
     اللبناني
    -0.07
    !.↵↵
    -0.07
    idential
    -0.07
    ears
    -0.07
     ]↵↵
    -0.07
    一度
    -0.06
    Forest
    -0.06
     Childhood
    -0.06
    התנהג
    -0.06
    ']))↵↵
    -0.06
    POSITIVE LOGITS
    (matches
    0.08
     poets
    0.07
    	wait
    0.07
    _PRESENT
    0.07
     raging
    0.07
    啼
    0.07
    (configuration
    0.07
     Goblin
    0.07
    _angles
    0.07
     Dys
    0.07
    Activations Density 0.023%

    No Known Activations