© 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. 18-TRANSCODER-HP
    7. 88873
    Prev
    Next
    INDEX
    Explanations

    tan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ested
    -0.30
    .getBody
    -0.27
    è¿Ļ座åŁİå¸Ĥ
    -0.27
     Operand
    -0.27
     OPS
    -0.26
    æĿ¡è¯Ħ论
    -0.25
    jure
    -0.25
    æľ¦èĥ§
    -0.25
    év
    -0.24
    TPL
    -0.24
    POSITIVE LOGITS
     surviving
    0.28
    lint
    0.28
     Spr
    0.26
    èħĪ
    0.25
     times
    0.25
     treat
    0.25
     wan
    0.25
     wait
    0.24
     overflow
    0.24
    elor
    0.24
    Activations Density 5.672%

    No Known Activations