© 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. 73177
    Prev
    Next
    INDEX
    Explanations

    general advice

    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
     Donald
    -0.08
    /io
    -0.08
     neutron
    -0.07
     lists
    -0.07
    Jur
    -0.07
     Logo
    -0.07
     Artikel
    -0.07
     Checklist
    -0.07
     Orlando
    -0.07
    Eine
    -0.06
    POSITIVE LOGITS
     unreasonable
    0.07
    composite
    0.07
    -food
    0.07
    츙
    0.07
    worthy
    0.07
    Welcome
    0.07
    샬
    0.06
    _shared
    0.06
     customerId
    0.06
     overly
    0.06
    Activations Density 0.494%

    No Known Activations