© 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. 69150
    Prev
    Next
    INDEX
    Explanations

    Citations

    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
    _sn
    -0.07
     conven
    -0.06
     thưởng
    -0.06
    ospital
    -0.06
    _human
    -0.06
     metic
    -0.06
    .Con
    -0.06
    NEL
    -0.06
     suchen
    -0.06
    -qu
    -0.06
    POSITIVE LOGITS
     transgender
    0.08
     fractured
    0.07
     שונה
    0.07
    TestCategory
    0.07
     classmates
    0.07
    apsible
    0.07
     kararı
    0.06
     książki
    0.06
    expire
    0.06
    "description
    0.06
    Activations Density 0.012%

    No Known Activations