© 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. 38961
    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
    agram
    -0.26
    çļĦè§Ĵèī²
    -0.25
    artment
    -0.25
    è§Ĵèī²
    -0.25
    atus
    -0.25
     II
    -0.24
     reflects
    -0.24
    ophil
    -0.24
     XII
    -0.24
    è¦ģåģļåĪ°
    -0.23
    POSITIVE LOGITS
    sbin
    0.28
    QUIT
    0.26
    空çĻ½
    0.26
    æĸ°èµĽåŃ£
    0.25
    EDURE
    0.24
     exon
    0.24
     SetValue
    0.24
    deriv
    0.24
    ForMember
    0.23
    ICE
    0.23
    Activations Density 0.028%

    No Known Activations

    This feature has no known activations.