© 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. 39067
    Prev
    Next
    INDEX
    Explanations

    scientific, technical language

    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
    éĩİ
    -0.30
     Excellence
    -0.28
    entina
    -0.27
    åħ³éĶ®æŶåĪ»
    -0.27
     Indices
    -0.26
    è¿Ļ家ä¼Ļ
    -0.24
    [keys
    -0.24
     Kle
    -0.24
    享çĶ¨
    -0.24
    仪
    -0.23
    POSITIVE LOGITS
    amon
    0.42
    lo
    0.34
    los
    0.32
    y
    0.32
    les
    0.32
    sects
    0.32
    mos
    0.32
    a
    0.31
    cond
    0.30
    lose
    0.30
    Activations Density 2.494%

    No Known Activations