© 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. 76256
    Prev
    Next
    INDEX
    Explanations

    semiconductors and electron-hole pairs

    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
     meis
    -0.07
    るべき
    -0.07
     normalized
    -0.07
     thẳng
    -0.07
    _SUM
    -0.06
     нескольких
    -0.06
    树林
    -0.06
     seperate
    -0.06
     Necessary
    -0.06
     opposing
    -0.06
    POSITIVE LOGITS
    lagen
    0.08
    vir
    0.08
     vacancy
    0.07
    persons
    0.07
    Program
    0.07
    diag
    0.07
     Society
    0.07
    谷歌
    0.07
     subsidy
    0.07
     orgas
    0.07
    Activations Density 0.011%

    No Known Activations