© 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. 31-TRANSCODER-HP
    7. 18365
    Prev
    Next
    INDEX
    Explanations

    thi

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isa
    -0.50
    is
    -0.40
    isi
    -0.36
    iso
    -0.34
    IS
    -0.33
    isia
    -0.32
    Iso
    -0.31
     Iso
    -0.31
    Is
    -0.30
    ISA
    -0.30
    POSITIVE LOGITS
    .feed
    0.27
    laden
    0.27
     ornament
    0.27
    edo
    0.26
    ONY
    0.26
    whelming
    0.25
    holm
    0.25
     Superintendent
    0.25
     Outer
    0.24
    atura
    0.24
    Activations Density 28.520%

    No Known Activations