© 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. 20093
    Prev
    Next
    INDEX
    Explanations

    unemployment and job seeking

    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
    膳食
    -0.07
    .Small
    -0.07
    сложн
    -0.07
     اسم
    -0.07
     Representative
    -0.07
     зависим
    -0.07
    颛
    -0.07
    ทาน
    -0.06
     Constraints
    -0.06
     heard
    -0.06
    POSITIVE LOGITS
    lus
    0.07
     Rita
    0.07
    kit
    0.07
    Items
    0.07
    PX
    0.07
     Riley
    0.07
    เทคน
    0.06
    бег
    0.06
     Phillips
    0.06
    强国
    0.06
    Activations Density 0.095%

    No Known Activations