© 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. 162434
    Prev
    Next
    INDEX
    Explanations

    Scientific/medical terms

    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
    ä¸Ĭæĸ¹
    -0.32
    thal
    -0.29
    etas
    -0.28
    段
    -0.27
     bom
    -0.26
    åı¸
    -0.25
    éĤ£æ®µ
    -0.25
    å®Ī
    -0.24
     Stam
    -0.23
    æĻļ
    -0.23
    POSITIVE LOGITS
    emachine
    0.25
    å¤ļä½ĻçļĦ
    0.25
    æĪĸå¤ļ
    0.25
    âĤĵ
    0.24
    {/
    0.24
    omet
    0.24
     Brief
    0.23
    anging
    0.23
     дÑĢÑĥгими
    0.23
     other
    0.23
    Activations Density 0.003%

    No Known Activations