© 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. 39920
    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
     normalized
    -0.27
     Dont
    -0.27
    jis
    -0.26
    etri
    -0.26
     cardi
    -0.25
     BaseModel
    -0.25
    -runner
    -0.25
     SaÄŁ
    -0.25
    uppy
    -0.25
     BRO
    -0.25
    POSITIVE LOGITS
    åİŁåĽłä¹ĭä¸Ģ
    0.27
    lei
    0.26
    ir
    0.26
    ious
    0.26
    oot
    0.26
    rep
    0.25
     Instrument
    0.25
    åħ·ä½ĵçļĦ
    0.25
    æ³ķå¾ĭ责任
    0.25
    âĤ¬
    0.24
    Activations Density 4.630%

    No Known Activations

    This feature has no known activations.