© 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. 162254
    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
    åı·åı¬
    -0.27
    unger
    -0.26
    ifter
    -0.26
    umberland
    -0.26
    åIJĵå¾Ĺ
    -0.26
    æŶå°ļ
    -0.25
    åIJĵ
    -0.24
    minster
    -0.24
     compliments
    -0.24
    olate
    -0.24
    POSITIVE LOGITS
    phys
    0.28
     ara
    0.26
    w
    0.26
    asure
    0.26
     Anth
    0.25
    zzle
    0.25
    Window
    0.25
     mess
    0.25
     Wol
    0.25
     maid
    0.25
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.