© 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. 33-TRANSCODER-HP
    7. 54289
    Prev
    Next
    INDEX
    Explanations

    spot

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    人æ°ij
    -0.31
    endas
    -0.29
     "[%
    -0.28
     spo
    -0.27
    第ä¸Ģå±Ĭ
    -0.26
     stew
    -0.25
    upe
    -0.25
     ак
    -0.24
    rem
    -0.24
    YW
    -0.24
    POSITIVE LOGITS
     part
    0.59
     spot
    0.50
    spot
    0.48
    éĥ¨åĪĨ
    0.47
     patch
    0.46
     parts
    0.43
    çļĦéĥ¨åĪĨ
    0.41
    patch
    0.40
     Spot
    0.39
     patches
    0.39
    Activations Density 0.277%

    No Known Activations