© 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. 39189
    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
     ноÑĢмалÑĮн
    -0.24
    æĮīè§Ħå®ļ
    -0.24
    .tap
    -0.24
    çĤ¸å¼¹
    -0.24
    å°ijäºĨ
    -0.23
    çļĦæľĢåIJİä¸Ģ
    -0.23
    ÙģÙĤ
    -0.23
    InSection
    -0.23
    两端
    -0.23
    osit
    -0.23
    POSITIVE LOGITS
    sus
    0.31
    å¼Ģ端
    0.28
    èĤĥ
    0.27
    isu
    0.26
     Sus
    0.24
    mel
    0.24
    rys
    0.24
    zech
    0.24
    SystemService
    0.24
    åĪĿæŃ¥
    0.24
    Activations Density 22.361%

    No Known Activations

    This feature has no known activations.