© 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. 40199
    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
    rance
    -0.29
    iode
    -0.28
    anse
    -0.27
    2
    -0.27
    ä¸ĩ人次
    -0.26
    Y
    -0.26
    type
    -0.26
     inception
    -0.25
    bed
    -0.25
    super
    -0.25
    POSITIVE LOGITS
     suggestive
    0.28
    å¿ĥåĬ¨
    0.27
     Sexy
    0.26
    ï¼ģ');↵
    0.24
    强çĥĪ
    0.24
     pleasures
    0.24
     sal
    0.24
    (ur
    0.23
    mites
    0.23
    (fh
    0.23
    Activations Density 13.658%

    No Known Activations

    This feature has no known activations.