© 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. 19-TRANSCODER-HP
    7. 9048
    Prev
    Next
    INDEX
    Explanations

    Code/documentation snippets

    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
    ighton
    -0.27
    æŬ
    -0.27
    .Hit
    -0.26
     Imperial
    -0.26
    paring
    -0.25
    ðŁĴ¾
    -0.25
    аÑĤÑĥÑĢ
    -0.25
    parator
    -0.25
    .Script
    -0.25
    ATURE
    -0.24
    POSITIVE LOGITS
    InThe
    0.29
    _us
    0.28
    è¹Ĭ
    0.27
    çĭ¸
    0.26
    Mex
    0.26
    _mex
    0.26
     Haram
    0.26
    ahead
    0.26
     ecc
    0.25
    eln
    0.25
    Activations Density 0.880%

    No Known Activations