© 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. 20-TRANSCODER-HP
    7. 142140
    Prev
    Next
    INDEX
    Explanations

    software development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Decor
    -0.28
    ddit
    -0.28
    ynn
    -0.25
    eln
    -0.25
    marsh
    -0.25
    è£ħ饰
    -0.25
     cvs
    -0.24
    .Async
    -0.24
    oons
    -0.24
    ãģijãĤĮãģ°
    -0.24
    POSITIVE LOGITS
     anymore
    0.28
    ãģªãĤĬãģ¾ãģĽãĤĵ
    0.27
    enthal
    0.25
    imat
    0.23
    iscal
    0.23
     streamline
    0.23
    éŃħ
    0.23
    ptides
    0.23
     cour
    0.23
    çł£
    0.22
    Activations Density 11.995%

    No Known Activations