© 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. 98195
    Prev
    Next
    INDEX
    Explanations

    code

    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
     Decompiled
    -0.29
    ingham
    -0.28
     déco
    -0.27
    orf
    -0.27
     Kapoor
    -0.26
     educated
    -0.25
    åģļä¸ĢäºĽ
    -0.25
    å°ıå§IJå§IJ
    -0.25
    heimer
    -0.25
    åĺĽ
    -0.24
    POSITIVE LOGITS
    ="__
    0.31
     Federation
    0.30
    wn
    0.29
     tops
    0.27
    –
    0.27
    --
    0.26
    ipher
    0.26
    multip
    0.25
    æijĩ
    0.25
    Y
    0.25
    Activations Density 0.003%

    No Known Activations