© 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. 112487
    Prev
    Next
    INDEX
    Explanations

    Source or origin

    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
     Gale
    -0.31
    ourd
    -0.28
    èĢIJ
    -0.26
     Plains
    -0.25
    -runner
    -0.25
    ancements
    -0.25
    èIJ½
    -0.24
    ³³³
    -0.23
    ças
    -0.23
     Âł Âł
    -0.23
    POSITIVE LOGITS
    è¾į
    0.27
    æ³½
    0.25
     ende
    0.24
    çĺ¿
    0.24
    å·½
    0.23
    col
    0.23
    itime
    0.23
    .join
    0.23
    omnia
    0.23
    å©ļ姻
    0.23
    Activations Density 0.006%

    No Known Activations