© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6796
    Prev
    Next
    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     *__
    -0.27
    è·Łä¸įä¸Ĭ
    -0.26
    -mobile
    -0.26
     feas
    -0.26
    ',[
    -0.25
    æĺ¯æĢİæł·
    -0.25
     slag
    -0.25
    aleigh
    -0.24
    ä¸įéĻIJ
    -0.24
    aks
    -0.23
    POSITIVE LOGITS
    AAC
    0.27
    ÑĢоÑģÑĤ
    0.26
    duit
    0.25
    ensus
    0.25
    held
    0.24
    bdb
    0.24
     mediator
    0.24
    umm
    0.23
    onymous
    0.23
    mir
    0.23
    Activations Density 0.077%

    No Known Activations