© 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. 8302
    Prev
    Next
    INDEX
    Explanations

    Non-English and Code

    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
    urat
    -0.28
    err
    -0.26
    vern
    -0.25
    ERNEL
    -0.25
     Carnegie
    -0.24
    ÑģÑĤÑĢоен
    -0.24
     Nobel
    -0.24
     thinner
    -0.24
     Generating
    -0.24
    \Input
    -0.24
    POSITIVE LOGITS
    Ups
    0.31
    第ä¸Ģéĥ¨
    0.29
    第ä¸Ģ家
    0.27
    çŁ³å®¶
    0.27
     Ups
    0.26
    ä¸¤å¼ł
    0.25
    请åıĬæŶ
    0.25
    èĢħçļĦ
    0.25
    sters
    0.25
     forwards
    0.24
    Activations Density 0.000%

    No Known Activations