© 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. 76588
    Prev
    Next
    INDEX
    Explanations

    apostrophe

    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
     QU
    -0.07
     comme
    -0.07
    (ns
    -0.07
    🛁
    -0.07
    leitung
    -0.07
    沃尔沃
    -0.06
     Swedish
    -0.06
    .trip
    -0.06
     quand
    -0.06
    чество
    -0.06
    POSITIVE LOGITS
     amateurs
    0.08
     rental
    0.08
    憾
    0.07
     Delegate
    0.07
     cues
    0.07
    hea
    0.07
    쎘
    0.07
     Intent
    0.07
    ors
    0.07
    _OLD
    0.06
    Activations Density 0.010%

    No Known Activations