© 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. 39662
    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
     exactly
    -0.26
    ä¸įæĺĵ
    -0.25
     sometimes
    -0.25
    太å°ij
    -0.24
     «
    -0.24
    zilla
    -0.24
    bish
    -0.24
     really
    -0.24
    chron
    -0.23
     понÑĢав
    -0.23
    POSITIVE LOGITS
    齿
    0.29
    å¹´ä¹ĭä¹ħ
    0.26
    ç¨İåĬ¡
    0.26
    æķĪ
    0.24
    ç½²
    0.23
    �t
    0.23
    -ticket
    0.23
    kommen
    0.23
    ket
    0.23
    safe
    0.22
    Activations Density 0.277%

    No Known Activations

    This feature has no known activations.