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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 88239
    Prev
    Next
    INDEX
    Explanations

    Excerpted sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Breitbart
    -0.27
    çĭ¬ä¸Ģ
    -0.27
    actal
    -0.27
    伤
    -0.26
    uilder
    -0.25
    轨
    -0.24
     Gund
    -0.24
    veau
    -0.24
    osas
    -0.24
    iar
    -0.24
    POSITIVE LOGITS
    人们çļĦ
    0.28
     %↵↵
    0.27
     moments
    0.26
    Vu
    0.25
    aji
    0.25
     çev
    0.25
    çıĤ
    0.24
    »↵↵
    0.24
    å¹³åĿĩæ°´å¹³
    0.24
     retrieved
    0.24
    Activations Density 0.003%

    No Known Activations