© 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. 163459
    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
    licit
    -0.27
    ucken
    -0.27
    lichkeit
    -0.26
    ause
    -0.26
    atis
    -0.25
    ucker
    -0.25
    ingo
    -0.25
    å±ij
    -0.25
    ès
    -0.24
    åħ¥åľº
    -0.24
    POSITIVE LOGITS
    %c
    0.28
     handset
    0.27
     Crafts
    0.26
    lements
    0.25
    ħ§
    0.24
    éķ¿çŁŃ
    0.24
    SKTOP
    0.24
    mares
    0.24
    ControlEvents
    0.23
    cers
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.