© 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. 15-RESID-POST-AA
    11. 72292
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ܘ
    -0.07
     nghĩ
    -0.07
    赏
    -0.07
     اختيار
    -0.06
    itter
    -0.06
    (s
    -0.06
    Move
    -0.06
     sóc
    -0.06
    _hosts
    -0.06
    _find
    -0.06
    POSITIVE LOGITS
    contained
    0.08
    nodiscard
    0.07
    实际控制
    0.07
    ](↵
    0.07
    encoded
    0.07
    Located
    0.06
    ollectors
    0.06
    AxisSize
    0.06
     che
    0.06
    RELEASE
    0.06
    Activations Density 0.006%

    No Known Activations