© 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. 39200
    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
    atee
    -0.24
    %C
    -0.23
    upy
    -0.23
    åĩıå°ijäºĨ
    -0.23
    åĩıå°ij
    -0.23
     reductions
    -0.22
    inged
    -0.22
    åįĩèµ·
    -0.22
    à¤
    -0.22
    好äºĭ
    -0.22
    POSITIVE LOGITS
    erner
    0.27
    çĶ³
    0.26
     Cros
    0.24
    TypeInfo
    0.23
     wn
    0.23
     sincere
    0.23
     accomplishment
    0.22
    èĽĻ
    0.22
    产ä¸ļç»ĵæŀĦ
    0.21
    avenport
    0.21
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.