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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 24196
    Prev
    Next
    INDEX
    Explanations

    instructions

    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
     rarely
    -0.27
    è¹Ħ
    -0.26
    æ²»çĹħ
    -0.26
    Lead
    -0.26
    çķĻç»Ļ
    -0.25
    íĤ¬
    -0.25
     Lead
    -0.24
    ä¸ĩ个
    -0.24
    eller
    -0.24
     Responsibility
    -0.24
    POSITIVE LOGITS
    è´§æºIJ
    0.29
    çķĮå®ļ
    0.29
    éģ´
    0.28
    ç¡®ç«ĭ
    0.28
     define
    0.28
     determine
    0.28
    å®ļä¹ī
    0.28
    æĢĿèĢĥ
    0.27
     determining
    0.27
    çĨŁæĤī
    0.26
    Activations Density 0.000%

    No Known Activations