© 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. 107916
    Prev
    Next
    INDEX
    Explanations

    Code snippets and technical documents

    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
    Stores
    -0.25
     container
    -0.25
    客
    -0.25
    Volumes
    -0.24
     Curtain
    -0.24
    æľįåĬ¡æľºæŀĦ
    -0.24
    CTOR
    -0.24
     demos
    -0.23
     Avalanche
    -0.23
     PARTY
    -0.23
    POSITIVE LOGITS
    å±ķ
    0.29
    enor
    0.26
    çĭ¬
    0.25
     phrase
    0.25
    ness
    0.25
    å§Ķç»Ħç»ĩ
    0.25
    eph
    0.25
    clearfix
    0.24
     im
    0.23
    its
    0.23
    Activations Density 0.191%

    No Known Activations