© 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. 7-RESID-POST-AA
    11. 59916
    Prev
    Next
    INDEX
    Explanations

    cloudy

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ﰐ
    -0.07
     ingredients
    -0.07
     VIR
    -0.07
     foi
    -0.07
     significance
    -0.07
     cặp
    -0.07
     milk
    -0.06
    韵味
    -0.06
     vibe
    -0.06
    asis
    -0.06
    POSITIVE LOGITS
    Current
    0.07
     deterministic
    0.07
     felony
    0.07
    _THEME
    0.07
    搓
    0.07
     כאשר
    0.07
    �
    0.07
    זמ
    0.07
    	headers
    0.06
    	statement
    0.06
    Activations Density 0.002%

    No Known Activations