© 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. 162453
    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
    .Cursors
    -0.28
    (getClass
    -0.27
    CHIP
    -0.26
     Age
    -0.26
    ader
    -0.25
    hue
    -0.24
    ارÙĬ
    -0.24
    acula
    -0.24
    aco
    -0.24
    ogl
    -0.24
    POSITIVE LOGITS
    å°ıç¼ĸä¸Ģèµ·
    0.30
    æ¼ıæ°´
    0.28
    iks
    0.26
    å¥ĹæĪ¿
    0.25
    raise
    0.25
     вним
    0.24
    åħ³æ³¨
    0.24
     piss
    0.24
    erce
    0.24
    .ready
    0.23
    Activations Density 0.009%

    No Known Activations

    This feature has no known activations.