© 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. 19515
    Prev
    Next
    INDEX
    Explanations

    launch

    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
    æĹ©æĹ©
    -0.29
    nore
    -0.28
    å¾Ģå¤ĸ
    -0.27
    两年åīį
    -0.26
    tin
    -0.26
    註
    -0.26
    Tre
    -0.25
    tas
    -0.25
    annes
    -0.25
    pit
    -0.25
    POSITIVE LOGITS
     launch
    0.39
    launch
    0.36
     Launch
    0.36
    Launch
    0.35
     launches
    0.34
    -launch
    0.31
    .launch
    0.31
    åĬ¨
    0.31
    aunch
    0.30
    åIJ¯åĬ¨
    0.29
    Activations Density 5.308%

    No Known Activations