© 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. 39424
    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
    greens
    -0.30
    earing
    -0.27
    ·»
    -0.27
    æĹıèĩªæ²»
    -0.26
    æĬ¥éĶĢ
    -0.25
    multipart
    -0.25
    åĪĨæľŁ
    -0.24
    çļĦçľ¼åħī
    -0.24
    ampo
    -0.24
     hindsight
    -0.24
    POSITIVE LOGITS
    转åıĺ
    0.33
    饼
    0.28
     frequencies
    0.27
    6
    0.25
    9
    0.25
     oscill
    0.25
    4
    0.25
    3
    0.25
     Frequ
    0.24
    并ä¸įä¼ļ
    0.24
    Activations Density 39.566%

    No Known Activations

    This feature has no known activations.