© 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. 30-TRANSCODER-HP
    7. 95549
    Prev
    Next
    INDEX
    Explanations

    US states and jurisdictions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     region
    -0.32
    sb
    -0.30
     regions
    -0.29
    æ¸ļ
    -0.28
    isha
    -0.28
    çľģå¸Ĥ
    -0.28
    åĽ½å®¶
    -0.28
    ometown
    -0.27
    èĮĥ
    -0.27
    éĴ¤
    -0.27
    POSITIVE LOGITS
    çļĦæīĢæľī
    0.34
    apeut
    0.29
     every
    0.29
     unheard
    0.28
    every
    0.28
    æīĢæľī
    0.27
    æīĢæľīçļĦ
    0.27
    Unit
    0.26
    åIJ¬åIJ¬
    0.26
    =all
    0.26
    Activations Density 0.884%

    No Known Activations