© 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. 24696
    Prev
    Next
    INDEX
    Explanations

    improvement

    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
     {
    -0.27
    æ¤Ł
    -0.26
     prox
    -0.26
    {Name
    -0.25
     ·
    -0.25
     cél
    -0.25
    erial
    -0.25
    ạn
    -0.24
    æŁIJ个
    -0.24
    empt
    -0.24
    POSITIVE LOGITS
    å¤ļæł·æĢ§
    0.37
    稳å®ļæĢ§
    0.34
    丰å¯Įå¤ļ彩
    0.33
    å±Ĥ次
    0.32
     realism
    0.31
    æľįåĬ¡æ°´å¹³
    0.31
    ä¸įæĸŃå®ĮåĸĦ
    0.31
     diversified
    0.31
     stability
    0.31
     completeness
    0.30
    Activations Density 0.003%

    No Known Activations