© 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. 128341
    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_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
    itures
    -0.07
     ogłoszeni
    -0.07
    '''
↵
    -0.07
    逦
    -0.07
    ën
    -0.06
    ':"
    -0.06
    佛山市
    -0.06
     breast
    -0.06
    Ⲟ
    -0.06
    杨幂
    -0.06
    POSITIVE LOGITS
     depend
    0.07
    .pop
    0.07
     tabletop
    0.07
     famously
    0.07
     dependency
    0.07
     Depths
    0.06
     contextual
    0.06
    团队
    0.06
    速度快
    0.06
    短缺
    0.06
    Activations Density 0.005%

    No Known Activations