© 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. 39073
    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
    uale
    -0.25
    ÙģÙĪر
    -0.25
     мо
    -0.24
    BOVE
    -0.24
    تÙĤد
    -0.24
    åį³
    -0.23
    à¹Ĥà¸Ĭ
    -0.23
    ibile
    -0.23
    bara
    -0.23
    IGHL
    -0.23
    POSITIVE LOGITS
    çĸ¾
    0.31
    代è¨Ģ
    0.25
    æ´»çĿĢ
    0.25
    åĴĢ
    0.25
     boolean
    0.25
    ï¼ŁãĢį
    0.25
     legalized
    0.25
     /*#__
    0.25
    åıijçĥŃ
    0.24
    æİĴè¡Įæ¦ľ
    0.24
    Activations Density 12.481%

    No Known Activations

    This feature has no known activations.