© 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. 12138
    Prev
    Next
    INDEX
    Explanations

    one

    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
     compensate
    -0.07
     וכמובן
    -0.07
     heavily
    -0.07
    这么说
    -0.07
     problemas
    -0.06
    への
    -0.06
     다만
    -0.06
     würde
    -0.06
     😉
    -0.06
    名叫
    -0.06
    POSITIVE LOGITS
    year
    0.08
    .L
    0.07
     boats
    0.07
     ye
    0.07
    atische
    0.07
    коло
    0.07
    曙
    0.07
    _y
    0.07
    From
    0.07
    術
    0.06
    Activations Density 0.005%

    No Known Activations