© 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. 15-RESID-POST-AA
    11. 15729
    Prev
    Next
    INDEX
    Explanations

    There

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    皈
    -0.08
    tic
    -0.07
    vide
    -0.07
    ugh
    -0.07
    потен
    -0.07
    تسويق
    -0.07
    iske
    -0.07
    عط
    -0.07
    켬
    -0.06
    ace
    -0.06
    POSITIVE LOGITS
    IDADE
    0.08
     LLP
    0.08
     REPL
    0.07
    秬
    0.07
    サイズ
    0.07
    以内
    0.07
    QDebug
    0.07
     plaintiffs
    0.07
     maxY
    0.07
     tamaño
    0.07
    Activations Density 0.001%

    No Known Activations