© 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. 163507
    Prev
    Next
    INDEX
    Explanations

    Technical writing

    np_max-act · gemini-2.0-flash
    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
    åĬŀ好
    -0.28
     remote
    -0.27
    ãģ¨æĢĿãģ£ãģ¦ãģĦãģŁ
    -0.27
     expression
    -0.27
    vvm
    -0.26
     Lis
    -0.25
    ãĤ¸ãĤ§
    -0.25
    çŁ³å®¶
    -0.24
     card
    -0.24
    jsx
    -0.24
    POSITIVE LOGITS
    èĦIJ
    0.28
    Impossible
    0.27
    “All
    0.27
    ++++++++
    0.26
    (ele
    0.26
    SION
    0.25
    çľĭçĤ¹
    0.25
    -Nov
    0.25
    (nb
    0.24
    “And
    0.24
    Activations Density 0.021%

    No Known Activations