© 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. 33-TRANSCODER-HP
    7. 53407
    Prev
    Next
    INDEX
    Explanations

    electron microscopy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éªĸ
    -0.27
     Air
    -0.27
    æŁ¥çľĭ详æĥħ
    -0.27
    à®Ł
    -0.26
    urement
    -0.26
    Air
    -0.25
    æł¼
    -0.25
    åıĶ
    -0.25
    stance
    -0.25
    Leap
    -0.25
    POSITIVE LOGITS
    guna
    0.30
    ä½ļ
    0.26
    æľ¬è½®
    0.26
    rounded
    0.25
     horns
    0.24
    aylor
    0.24
    heads
    0.24
    ç¢Ĺ
    0.24
     buffalo
    0.23
    ège
    0.23
    Activations Density 0.012%

    No Known Activations