© 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. 19-RESID-POST-AA
    11. 12561
    Prev
    Next
    INDEX
    Explanations

    say "ending with commas"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    近三年
    -0.06
    修身
    -0.06
    主管部门
    -0.06
    Dic
    -0.06
     merges
    -0.06
    大队
    -0.06
    _cells
    -0.06
    领导者
    -0.06
    合并
    -0.06
     calculus
    -0.06
    POSITIVE LOGITS
    (xi
    0.07
    Touch
    0.07
    (className
    0.07
     Bowling
    0.07
    .Class
    0.06
    NSNotification
    0.06
    برنامج
    0.06
    (ct
    0.06
     שאני
    0.06
    	glBind
    0.06
    Activations Density 0.021%

    No Known Activations