© 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. 41821
    Prev
    Next
    INDEX
    Explanations

    play

    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
    STA
    -0.27
    tere
    -0.26
    åįĴ
    -0.25
    è¶ĭ
    -0.25
    flake
    -0.25
    浸
    -0.24
    otas
    -0.24
    blings
    -0.24
     scrapped
    -0.24
    ulent
    -0.23
    POSITIVE LOGITS
     significant
    0.37
     key
    0.35
    éĩį大
    0.34
     significantly
    0.34
     central
    0.33
     big
    0.32
    éĩįè¦ģ
    0.32
     driving
    0.31
    åħ³éĶ®
    0.29
     core
    0.29
    Activations Density 0.007%

    No Known Activations