© 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. 35-TRANSCODER-HP
    7. 40143
    Prev
    Next
    INDEX
    Explanations

    Scientific/Bacterial Texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vita
    -0.38
    olta
    -0.36
    ipa
    -0.36
    cta
    -0.36
    uta
    -0.35
    aba
    -0.35
    iza
    -0.35
    inka
    -0.34
    iya
    -0.34
    ika
    -0.34
    POSITIVE LOGITS
    ."\
    0.33
    .".
    0.30
    ”çļĦ
    0.29
    äll
    0.29
    .”
    0.28
    ellar
    0.28
    ELL
    0.28
    ."
    0.28
    elles
    0.28
    ecc
    0.28
    Activations Density 0.136%

    No Known Activations