© 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. 39142
    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
     Hop
    -0.28
     suprem
    -0.27
     perf
    -0.26
    âĨĹ
    -0.25
    contro
    -0.25
     perverse
    -0.25
    há»ķ
    -0.24
     neighbor
    -0.24
    è¿ĻèĪ¬
    -0.23
     different
    -0.23
    POSITIVE LOGITS
    Choice
    0.30
    webs
    0.29
    icos
    0.27
    -eng
    0.27
    ias
    0.27
    assist
    0.26
     cylinders
    0.26
    -install
    0.25
    holders
    0.25
    çĻ»
    0.25
    Activations Density 21.062%

    No Known Activations

    This feature has no known activations.