© 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. 32-TRANSCODER-HP
    7. 41311
    Prev
    Next
    INDEX
    Explanations

    night

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     only
    -1.30
    ä»ħ
    -1.27
    only
    -1.27
    Only
    -1.23
    -only
    -1.21
     Only
    -1.18
    åıª
    -1.17
    _only
    -1.16
    åıªæľī
    -1.10
    ONLY
    -1.08
    POSITIVE LOGITS
    [keys
    0.25
    åĪĨåĮº
    0.24
    ells
    0.23
    theses
    0.23
    isters
    0.23
    rimon
    0.22
    oen
    0.22
    骥
    0.22
    osphere
    0.22
    åIJĦè¡ĮåIJĦ
    0.22
    Activations Density 0.003%

    No Known Activations