© 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. 130058
    Prev
    Next
    INDEX
    Explanations

    Alphanumeric data

    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
    å¤ļå°ij
    -0.30
    ..
    -0.27
     c
    -0.27
    |
    -0.26
     conc
    -0.25
    Âł
    -0.25
    åĮ¡
    -0.25
    ?
    -0.25
     da
    -0.24
    eling
    -0.24
    POSITIVE LOGITS
    ä¸Ģç«Ļ
    0.31
    äºĭæķħåıijçĶŁ
    0.28
    è°ģçŁ¥éģĵ
    0.28
    oki
    0.26
     setStatus
    0.26
     specimen
    0.26
     prosec
    0.25
     oko
    0.25
    ä»Ķ
    0.25
     ACPI
    0.25
    Activations Density 0.001%

    No Known Activations