© 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. 39225
    Prev
    Next
    INDEX
    Explanations

    played

    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
    å¸ĮæľĽèĥ½å¤Ł
    -0.29
    appro
    -0.28
     exactly
    -0.28
     approaching
    -0.28
     attempted
    -0.27
    ãģ¨èĢĥãģĪ
    -0.26
    serter
    -0.25
     deter
    -0.25
    æĮīçħ§
    -0.25
     observing
    -0.25
    POSITIVE LOGITS
    eled
    0.29
    AFE
    0.28
    ä¿©
    0.27
    (cm
    0.26
    Ñĥк
    0.26
    å²³
    0.26
    xaf
    0.25
     âĶľ
    0.24
    Defs
    0.24
    (AF
    0.24
    Activations Density 33.208%

    No Known Activations