© 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. 162616
    Prev
    Next
    INDEX
    Explanations

    commas and conjunctions

    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
    客åķĨ
    -0.30
    ethylene
    -0.29
    侧
    -0.28
     PARAMETERS
    -0.27
    榻
    -0.26
    parameter
    -0.26
    ä»»æĢ§
    -0.26
     Assigned
    -0.25
    assigned
    -0.25
    åĽłåŃIJ
    -0.25
    POSITIVE LOGITS
    éĩĬ
    0.32
    ulares
    0.28
    ä¸įçŁ¥
    0.26
     unsuccessfully
    0.25
     versions
    0.25
    æĪIJåĬŁçļĦ
    0.25
    åı¸
    0.24
    liest
    0.24
     noticeably
    0.24
    è¯Ĩ
    0.24
    Activations Density 0.001%

    No Known Activations