© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 163219
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xAF
    -0.28
    åĻİ
    -0.27
    essaging
    -0.27
    æĪĽ
    -0.26
    çĶŃ
    -0.26
    <Component
    -0.25
    æİĴåIJį第
    -0.25
    gow
    -0.25
     WebClient
    -0.25
    个çĻ¾åĪĨ
    -0.24
    POSITIVE LOGITS
    inois
    0.28
    imals
    0.25
    il
    0.25
    èŁij
    0.25
    idal
    0.25
    alsa
    0.25
     aluminium
    0.24
    æ¡IJ
    0.24
    lift
    0.23
    tl
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.