© 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. 27-TRANSCODER-HP
    7. 57314
    Prev
    Next
    INDEX
    Explanations

    Code/technical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     preceding
    -0.25
    ä¸Ĭåīį
    -0.25
    室
    -0.25
    çĨŁæĤīçļĦ
    -0.25
    ä¸Ĭå¹´
    -0.25
    çĵ£
    -0.25
     Harmon
    -0.24
    åīįéĿ¢
    -0.24
    ä¸Ĭä¸ĸ纪
    -0.24
    <cv
    -0.24
    POSITIVE LOGITS
     later
    0.51
    åIJİç»Ń
    0.51
     afterwards
    0.50
    以åIJİ
    0.50
    later
    0.49
    ä¹ĭåIJİ
    0.49
    åIJİçļĦ
    0.47
    å¾ĢåIJİ
    0.47
     after
    0.47
    after
    0.47
    Activations Density 0.001%

    No Known Activations