© 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. 163825
    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
    endon
    -0.26
    éĻIJãĤĬ
    -0.25
    ä¸ĩæĪ·
    -0.25
    enders
    -0.24
    opoulos
    -0.24
     Initialized
    -0.23
    washer
    -0.23
    รม
    -0.23
    itzer
    -0.22
    igy
    -0.22
    POSITIVE LOGITS
     thr
    0.27
     PIT
    0.25
     longest
    0.25
    讳
    0.24
    bomb
    0.24
    .drag
    0.24
    UNK
    0.24
    Unmount
    0.24
    Æ°ng
    0.23
     bomb
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.