© 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
    2. Qwen3-4B
    3. 35-TRANSCODER-HP
    4. 39966
    Prev
    Next
    INDEX
    Explanations

    "us" and "unusable"

    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
    tent
    -0.25
    -items
    -0.25
     packs
    -0.25
    -org
    -0.25
     narration
    -0.25
     commissions
    -0.24
     CDs
    -0.24
    å¸Ĥæ°ij
    -0.24
    ties
    -0.24
    -Jan
    -0.23
    POSITIVE LOGITS
    unable
    0.33
    leep
    0.33
    erokee
    0.31
    une
    0.31
    isy
    0.30
    uch
    0.30
    hiro
    0.30
    etsk
    0.30
    phis
    0.29
    estar
    0.29
    Activations Density 1.900%

    No Known Activations