© 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. 32-TRANSCODER-HP
    7. 41926
    Prev
    Next
    INDEX
    Explanations

    foreign language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yst
    -0.27
    hell
    -0.26
    yles
    -0.26
     Helm
    -0.25
    helm
    -0.25
    æĮģæľīçļĦ
    -0.25
    inactive
    -0.24
    ä¸Ģ对ä¸Ģ
    -0.24
    luck
    -0.24
    å°¼æĸ¯
    -0.24
    POSITIVE LOGITS
    è½½
    0.29
    ocop
    0.29
    åħµåĽ¢
    0.27
    aroo
    0.26
    ocre
    0.26
    çĶ«
    0.25
    egr
    0.25
    è¼ī
    0.25
    orks
    0.25
    ãĤ«ãĥª
    0.25
    Activations Density 0.001%

    No Known Activations