© 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. 39977
    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
    atom
    -0.31
    ATOM
    -0.27
    rays
    -0.27
    åŃĺéĩı
    -0.26
    itter
    -0.25
    istra
    -0.25
    azu
    -0.24
    ä¸Ģç¬Ķ
    -0.24
     tre
    -0.24
     WindowManager
    -0.24
    POSITIVE LOGITS
    utions
    0.28
    quet
    0.26
     Heck
    0.24
     enf
    0.24
    furt
    0.24
    éģģ
    0.23
    führ
    0.23
    ackers
    0.23
    enance
    0.23
    asers
    0.23
    Activations Density 0.651%

    No Known Activations

    This feature has no known activations.