© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162988
    Prev
    Next
    INDEX
    Explanations

    varieties

    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
    ç³Ł
    -0.30
    reu
    -0.29
    è¿Ļæīį
    -0.24
    artner
    -0.24
    æĢ»ç®Ĺ
    -0.24
    arter
    -0.23
    ìŀł
    -0.23
    èĤļåŃIJ
    -0.23
    èĢģå¸ĪçļĦ
    -0.23
    æ©Ħæ¦Ħ
    -0.23
    POSITIVE LOGITS
    able
    0.32
     no
    0.29
    ä¸ŀ
    0.27
    atic
    0.26
    ousand
    0.26
     channel
    0.25
    æľŁåĨħ
    0.25
    æĪĸèĢħæĺ¯
    0.25
     guide
    0.25
     ZERO
    0.25
    Activations Density 0.004%

    No Known Activations