© 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. 39765
    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
    .mdl
    -0.25
     risking
    -0.25
    dea
    -0.25
    æıŃå¼Ģ
    -0.24
    bers
    -0.24
    èĢģå¸Ī们
    -0.23
    ctions
    -0.23
    kt
    -0.23
    äºĮæĺ¯
    -0.23
    å±ī
    -0.23
    POSITIVE LOGITS
    atsu
    0.26
    vak
    0.26
    oux
    0.26
    大åݦ
    0.25
     domest
    0.25
    çķħ
    0.24
    ä¸ªå·¥ä½ľ
    0.24
    avs
    0.24
    uts
    0.24
    spath
    0.24
    Activations Density 5.892%

    No Known Activations

    This feature has no known activations.