© 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. 89808
    Prev
    Next
    INDEX
    Explanations

    software and copyright

    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
    麻çĹ¹
    -0.27
    å¤ĩæĪĺ
    -0.27
    wik
    -0.26
     Fifty
    -0.25
    ÑĢог
    -0.25
    ç¥Ŀè´º
    -0.25
    PathParam
    -0.25
    iley
    -0.24
     Fill
    -0.24
     neutrality
    -0.24
    POSITIVE LOGITS
    ç²ķ
    0.27
    æĹ©æľŁ
    0.26
     cross
    0.26
     Maar
    0.25
     early
    0.25
    ìľ¼ë©´
    0.24
    ames
    0.24
    är
    0.24
    assium
    0.24
    uento
    0.24
    Activations Density 7.908%

    No Known Activations