© 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. 12-TRANSCODER-HP
    7. 22931
    Prev
    Next
    INDEX
    Explanations

    Medical/technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     compressed
    -0.29
    åİĭ缩
    -0.28
    gzip
    -0.28
     quoi
    -0.28
    Zip
    -0.26
    èĢĦ
    -0.26
     pack
    -0.26
     compress
    -0.25
    zip
    -0.25
     armored
    -0.25
    POSITIVE LOGITS
    fu
    0.30
    aton
    0.27
    ç®Ĺæ³ķ
    0.25
     {{
    0.25
    esk
    0.25
    è¯ŀçĶŁ
    0.25
    æ¸ħç®Ĺ
    0.24
    侦
    0.24
    ita
    0.24
    acen
    0.24
    Activations Density 0.005%

    No Known Activations