© 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. 162544
    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
    -----
    -0.26
     brought
    -0.26
    å±¥
    -0.25
    è½½
    -0.25
    -------
    -0.25
    COPY
    -0.25
    mere
    -0.25
    å¸Ĥåľºä¸Ĭ
    -0.24
    .createFrom
    -0.24
    ustain
    -0.24
    POSITIVE LOGITS
    ä¸ĵåľº
    0.27
    viso
    0.26
     deluxe
    0.26
    ulous
    0.26
    åIJijãģį
    0.25
    eken
    0.25
    sound
    0.25
    opic
    0.24
    ankan
    0.24
    arak
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.