© 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. 89300
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æĺıè¿·
    -0.27
    åįĥåħĥ
    -0.27
    fall
    -0.26
    (:,:,
    -0.26
    imonials
    -0.26
    æĤ¨
    -0.26
    åĪĨ享
    -0.26
     sharing
    -0.25
    åĿIJä¸ĭ
    -0.25
    éħIJ
    -0.25
    POSITIVE LOGITS
    ivant
    0.28
    seys
    0.27
    ä½ľä¸ºä¸Ģç§į
    0.27
    {{{
    0.26
    '])->
    0.26
    >{!!
    0.25
    æĪĺçķ¥æĢ§
    0.25
    èĹł
    0.24
     facets
    0.24
     "{{
    0.24
    Activations Density 2.019%

    No Known Activations

    This feature has no known activations.