© 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. 22-TRANSCODER-HP
    7. 130056
    Prev
    Next
    INDEX
    Explanations

    Code snippets, versions, dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arser
    -0.27
    emon
    -0.26
    sgiving
    -0.25
     expert
    -0.25
    quant
    -0.25
     harder
    -0.25
     too
    -0.24
    ems
    -0.24
     general
    -0.24
    acea
    -0.24
    POSITIVE LOGITS
     THEN
    0.27
    容
    0.27
    ihn
    0.26
    åĩłå¹´
    0.25
    ughters
    0.25
    é¾Ľ
    0.25
    åĩłåįģå¹´
    0.25
    öyle
    0.25
    ulen
    0.25
    lops
    0.24
    Activations Density 0.023%

    No Known Activations