© 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. 5452
    Prev
    Next
    INDEX
    Explanations

    video encoding with x264

    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_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
    umu
    -0.07
    禀
    -0.07
    OURSE
    -0.07
    的态度
    -0.07
    %x
    -0.07
     Beard
    -0.07
    人参
    -0.07
    扫一扫
    -0.07
    .DisplayName
    -0.06
     الحوثي
    -0.06
    POSITIVE LOGITS
    hasil
    0.07
     giải
    0.07
    #SBATCH
    0.07
    ée
    0.07
     usually
    0.07
    lsruhe
    0.06
     nhằm
    0.06
    _AL
    0.06
     rather
    0.06
     бесплат
    0.06
    Activations Density 0.001%

    No Known Activations