© 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. 18-TRANSCODER-HP
    7. 89221
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etAddress
    -0.29
     INLINE
    -0.26
    ITA
    -0.25
    BOT
    -0.25
     fund
    -0.24
    etype
    -0.24
    endon
    -0.24
    uft
    -0.24
    keit
    -0.24
    atrix
    -0.24
    POSITIVE LOGITS
    misc
    0.26
    ilmiÅŁ
    0.25
    ìľ
    0.25
     Wolfe
    0.25
     entered
    0.24
    ,copy
    0.23
    éºĴéºŁ
    0.23
    éĢīåĿĢ
    0.23
    èĪī
    0.23
    åįĩèµ·
    0.23
    Activations Density 2.603%

    No Known Activations