© 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. 89247
    Prev
    Next
    INDEX
    Explanations

    code/technical text

    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
    è´Łè´£
    -0.29
    èģĶåIJĪä¼ļ
    -0.28
    eve
    -0.27
     patch
    -0.27
     expectations
    -0.26
    iap
    -0.26
    æĬľ
    -0.26
    ä¸ĭåıij
    -0.26
    忽
    -0.25
    evt
    -0.25
    POSITIVE LOGITS
    åIJĪéĢĤ
    0.35
    $max
    0.29
    æľĢåIJĪéĢĤ
    0.28
    lsa
    0.28
    å¿ĥ仪
    0.27
     preferred
    0.26
     suitability
    0.25
    preferred
    0.25
    æľĢåıĹ欢è¿İ
    0.25
     Suitable
    0.25
    Activations Density 51.040%

    No Known Activations