© 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. 31-TRANSCODER-HP
    7. 19016
    Prev
    Next
    INDEX
    Explanations

    scientific or technical descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ°Ķ
    -0.38
     air
    -0.30
    æ°£
    -0.30
     Air
    -0.27
    _GU
    -0.26
    [sizeof
    -0.25
    air
    -0.25
    acios
    -0.25
    空æ°Ķ
    -0.24
     fun
    -0.24
    POSITIVE LOGITS
    åįĬ天
    0.29
     sem
    0.28
     labyrinth
    0.28
    èµĽ
    0.28
    ewidth
    0.27
    è³½
    0.27
     penny
    0.27
    ãĥĽãĥ¼ãĥ«
    0.26
     semi
    0.26
    lich
    0.25
    Activations Density 0.098%

    No Known Activations