© 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. 111968
    Prev
    Next
    INDEX
    Explanations

    mountain

    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
    åĩĨ
    -0.30
    nings
    -0.29
    propri
    -0.27
    sav
    -0.26
    sumer
    -0.26
    $a
    -0.25
    mez
    -0.25
    MI
    -0.24
     Consumer
    -0.24
    æİī
    -0.24
    POSITIVE LOGITS
    ide
    0.28
    å´©
    0.24
    egers
    0.24
     bi
    0.24
     condensed
    0.23
    bial
    0.23
    cape
    0.23
    ality
    0.23
    achusetts
    0.23
    IMUM
    0.23
    Activations Density 0.121%

    No Known Activations