© 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. 41690
    Prev
    Next
    INDEX
    Explanations

    Computer/technical texts

    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
    çļĦåľŁåľ°
    -0.29
    åľŁåľ°
    -0.26
    èĬĻèĵī
    -0.26
    åĨĴ
    -0.26
    avel
    -0.25
    rones
    -0.24
    amic
    -0.24
     Finished
    -0.24
    ä¸¤å¼ł
    -0.24
    anto
    -0.24
    POSITIVE LOGITS
    ħ§
    0.30
    èĢģå®ŀ
    0.28
    _exports
    0.27
    nuts
    0.26
    TEX
    0.25
    oxy
    0.25
    enumerator
    0.25
    åľº
    0.25
    rom
    0.25
    oubted
    0.24
    Activations Density 0.002%

    No Known Activations