© 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. 95763
    Prev
    Next
    INDEX
    Explanations

    =

    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
    שפע
    -0.07
    来说
    -0.07
    赞成
    -0.06
    組織
    -0.06
     ally
    -0.06
     lake
    -0.06
    Acts
    -0.06
     wake
    -0.06
    waves
    -0.06
     Seas
    -0.06
    POSITIVE LOGITS
     subordinate
    0.08
     predominantly
    0.07
    颇有
    0.07
    erializer
    0.07
    _epochs
    0.07
    电视机
    0.07
    _PROM
    0.07
    AndUpdate
    0.07
     initialized
    0.07
     fallback
    0.07
    Activations Density 0.019%

    No Known Activations