© 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. 39866
    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
    çŃ¾åIJį
    -0.30
     kino
    -0.27
     personalities
    -0.26
    æĹłæķ°
    -0.26
    IRON
    -0.26
    代
    -0.25
    spe
    -0.25
    æĿ¥åĪ°
    -0.24
    主ä¹ī
    -0.24
    éĽĩä½£
    -0.24
    POSITIVE LOGITS
    False
    0.27
    lat
    0.26
     háºŃu
    0.26
    é«Ģ
    0.26
    esz
    0.26
     express
    0.26
     aggregate
    0.26
     tả
    0.25
     "%
    0.25
    缮çļĦ
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.