© 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. 41655
    Prev
    Next
    INDEX
    Explanations

    Initialisms and ship names

    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
    berger
    -0.28
    uzzi
    -0.28
    ç»Ħè£ħ
    -0.26
    egis
    -0.25
    ALES
    -0.25
    oug
    -0.25
    -bel
    -0.24
    eg
    -0.24
    ughs
    -0.24
    çļĦåį°è±¡
    -0.24
    POSITIVE LOGITS
    OND
    0.30
    FT
    0.29
    æĪĺ
    0.28
    af
    0.26
    QP
    0.25
    穹
    0.25
    ä»İæѤ
    0.24
    éĽį
    0.24
    åIJij举
    0.24
     Palm
    0.24
    Activations Density 0.005%

    No Known Activations