© 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. 89238
    Prev
    Next
    INDEX
    Explanations

    measuring cups

    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
    ["_
    -0.24
    iams
    -0.24
    ä¿Ŀå®Ī
    -0.24
    up
    -0.24
     conserve
    -0.23
    before
    -0.23
    adt
    -0.23
    bef
    -0.23
    _eps
    -0.23
    ::-
    -0.23
    POSITIVE LOGITS
    lying
    0.32
    erator
    0.28
    æį¢äºĨ
    0.28
     dint
    0.26
    lical
    0.26
    acity
    0.26
    ombs
    0.26
    lications
    0.24
    BERS
    0.24
    lotte
    0.24
    Activations Density 11.415%

    No Known Activations