© 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. 142156
    Prev
    Next
    INDEX
    Explanations

    Common english words

    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
     Readers
    -0.27
    anel
    -0.26
     enrich
    -0.25
    burg
    -0.25
    epad
    -0.25
    ä¸ĸçķĮè§Ĥ
    -0.24
    urger
    -0.23
    .ReadString
    -0.23
    esar
    -0.23
    çĿ«
    -0.23
    POSITIVE LOGITS
    Reviewed
    0.27
    ofs
    0.27
    acock
    0.26
    NULL
    0.26
    itives
    0.26
    åĮºåĪĨ
    0.25
     null
    0.24
    å¹´éĻIJ
    0.24
    lessness
    0.24
    orama
    0.24
    Activations Density 16.432%

    No Known Activations