© 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. 162642
    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
    ensation
    -0.27
    æ±
    -0.26
    èĪĴæľį
    -0.25
    วย
    -0.24
     GOLD
    -0.23
    al
    -0.23
    aters
    -0.23
    .tm
    -0.23
     der
    -0.23
     state
    -0.23
    POSITIVE LOGITS
    otec
    0.27
    chest
    0.26
     separately
    0.25
    |array
    0.25
    reate
    0.25
    èij«
    0.24
    ernal
    0.23
    ä¿Ŀå®ī
    0.23
    èĥĦ
    0.23
    udit
    0.23
    Activations Density 0.009%

    No Known Activations

    This feature has no known activations.