© 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. 23090
    Prev
    Next
    INDEX
    Explanations

    antibiotics

    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
     Closet
    -0.28
    ombat
    -0.27
    å°ĸåı«
    -0.27
    é¾Ļæ¹ĸ
    -0.26
    游æĪıæĵįä½ľ
    -0.26
    éļį
    -0.25
    åĤ²
    -0.25
    çĥ
    -0.24
    _dbg
    -0.24
    å¸Ĥå§Ķ书记
    -0.24
    POSITIVE LOGITS
    ECH
    0.28
    pled
    0.28
    ãĤ¦ãĤ§
    0.28
    .jquery
    0.26
    OPSIS
    0.26
     conc
    0.26
     Eis
    0.26
    æ§Ł
    0.25
    çIJĨ
    0.25
     credit
    0.25
    Activations Density 0.000%

    No Known Activations