© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 107624
    Prev
    Next
    INDEX
    Explanations

    cucumber

    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
     hemorrh
    -0.07
     Voltage
    -0.07
     physician
    -0.07
     Parking
    -0.07
    崶
    -0.07
    “They
    -0.07
     Guardian
    -0.06
    放假
    -0.06
     Campus
    -0.06
    徙
    -0.06
    POSITIVE LOGITS
     ativ
    0.07
     результат
    0.07
    étais
    0.07
     hizo
    0.07
    	strcat
    0.06
     <*
    0.06
    manız
    0.06
    _launch
    0.06
    )..
    0.06
    _ut
    0.06
    Activations Density 0.002%

    No Known Activations