© 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. 19-TRANSCODER-HP
    7. 5962
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ĥæĺŁ
    -0.29
    alité
    -0.27
    çļĦæĥħ
    -0.27
    --*/↵
    -0.26
    .ascii
    -0.26
    logfile
    -0.24
    (STD
    -0.24
    .Transactional
    -0.24
    discord
    -0.23
    ноÑģÑĤ
    -0.23
    POSITIVE LOGITS
     einf
    0.26
     chiefly
    0.25
     utan
    0.25
    ria
    0.24
    åĵº
    0.24
    容è²Į
    0.24
    ogue
    0.23
     setFrame
    0.23
    omin
    0.22
     countryCode
    0.22
    Activations Density 0.058%

    No Known Activations

    This feature has no known activations.