© 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. 39244
    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
     alerts
    -0.28
    æıIJåīį
    -0.27
    æıIJæĹ©
    -0.26
    çĥŃ线
    -0.26
     til
    -0.26
     hits
    -0.25
    -containing
    -0.25
    åħ³åĪĩ
    -0.25
     partitions
    -0.25
     hooks
    -0.25
    POSITIVE LOGITS
    oÄŁlu
    0.29
    æĺ¯ä»Ģä¹Īåij¢
    0.28
    onda
    0.28
    StackSize
    0.28
    ä»Ģä¹Īåij¢
    0.27
    (Stack
    0.27
    ç«ŀäºī对æīĭ
    0.27
    ány
    0.26
    .wikipedia
    0.26
    ä¸ĢèĦļ
    0.26
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.