© 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. 6988
    Prev
    Next
    INDEX
    Explanations

    website navigation

    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
    omic
    -0.29
    <cv
    -0.28
    olith
    -0.27
     perm
    -0.26
     pin
    -0.25
    åıĺäºĨ
    -0.24
     discriminatory
    -0.24
     Tex
    -0.24
    öm
    -0.23
    spect
    -0.23
    POSITIVE LOGITS
    ayo
    0.30
    ëĿ¼ëıĦ
    0.28
    .Abs
    0.28
     (__
    0.26
     horns
    0.26
    (?:
    0.25
    æİī
    0.25
    (abs
    0.24
     ASAP
    0.24
     Douglas
    0.23
    Activations Density 0.008%

    No Known Activations