© 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. 39588
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    dae
    -0.29
    afx
    -0.28
    aya
    -0.27
    -peer
    -0.25
    icum
    -0.24
    craper
    -0.24
    å¤Ł
    -0.24
    peare
    -0.24
    æŶåĪ»
    -0.24
    å¾ĪæŃ£å¸¸
    -0.24
    POSITIVE LOGITS
    Specification
    0.26
     pers
    0.26
     sides
    0.24
    utra
    0.24
     relation
    0.23
     sense
    0.23
     spill
    0.23
    éĶģ
    0.23
     flats
    0.23
     heavy
    0.23
    Activations Density 2.454%

    No Known Activations

    This feature has no known activations.