© 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. 39567
    Prev
    Next
    INDEX
    Explanations

    DNA prokaryotes eukaryotes

    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
    .hh
    -0.28
     Montgomery
    -0.26
    (kind
    -0.25
     OWN
    -0.25
    lä
    -0.25
     pó
    -0.24
    æĺİå¹´
    -0.24
    æĶ
    -0.24
    ology
    -0.24
     engineered
    -0.23
    POSITIVE LOGITS
    asure
    0.29
    zet
    0.29
    serter
    0.29
    ysi
    0.28
    æľµ
    0.28
    BAT
    0.26
    phe
    0.26
    CRET
    0.26
    uto
    0.26
    n
    0.26
    Activations Density 4.786%

    No Known Activations