© 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. 23-TRANSCODER-HP
    7. 24399
    Prev
    Next
    INDEX
    Explanations

    Adv

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ndo
    -0.27
    phan
    -0.26
    tron
    -0.26
    razier
    -0.25
    cores
    -0.25
     {[
    -0.24
    yte
    -0.24
     Seah
    -0.24
    an
    -0.24
    -start
    -0.24
    POSITIVE LOGITS
    aml
    0.28
    客æĪ·æıIJä¾Ľ
    0.28
    çŁ³å®¶
    0.26
     azt
    0.25
     latter
    0.24
    actory
    0.24
    ocal
    0.24
     Presbyterian
    0.23
    acam
    0.23
    å³Ħ
    0.23
    Activations Density 0.181%

    No Known Activations