© 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. 39060
    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
    YW
    -0.27
     Signup
    -0.25
    åĩ¿
    -0.24
    æį»
    -0.24
    .AI
    -0.24
     Dates
    -0.24
    ael
    -0.24
    pliant
    -0.23
     GetComponent
    -0.23
     Plans
    -0.23
    POSITIVE LOGITS
    åīĤ
    0.29
     stolen
    0.26
    rc
    0.25
    è°Ķ
    0.25
     rc
    0.24
    upon
    0.24
    estone
    0.24
    ло
    0.24
    chw
    0.24
    éĽī
    0.23
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.