© 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. 39604
    Prev
    Next
    INDEX
    Explanations

    veg

    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
    iani
    -0.29
    asu
    -0.29
    iana
    -0.29
    anie
    -0.28
     ans
    -0.28
    ania
    -0.27
    ane
    -0.27
    ani
    -0.27
    anes
    -0.27
    än
    -0.27
    POSITIVE LOGITS
    KHTML
    0.26
    pect
    0.26
    aspers
    0.26
     Apartment
    0.26
    clide
    0.26
    -drive
    0.24
    adopt
    0.24
     Spect
    0.24
    achts
    0.24
     indiv
    0.23
    Activations Density 1.751%

    No Known Activations