© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 69199
    Prev
    Next
    INDEX
    Explanations

    standards and specifications

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ny
    -0.07
    广大市民
    -0.07
    ניוז
    -0.07
    .getCurrentUser
    -0.07
    allen
    -0.07
    新闻记者
    -0.07
    党委书记
    -0.07
     encuent
    -0.07
     Moreno
    -0.07
    anyahu
    -0.07
    POSITIVE LOGITS
    ובת
    0.07
     Hint
    0.07
     bada
    0.07
    _context
    0.07
    ركة
    0.07
    _pemb
    0.07
    לת
    0.07
    ammer
    0.06
    markup
    0.06
    YSTEM
    0.06
    Activations Density 0.010%

    No Known Activations