© 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. 31-TRANSCODER-HP
    7. 18923
    Prev
    Next
    INDEX
    Explanations

    scientific/technical analysis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tables
    -0.33
    tables
    -0.31
    uell
    -0.30
     cuffs
    -0.29
    preter
    -0.27
    inox
    -0.26
    anon
    -0.26
    (DBG
    -0.25
     horizontally
    -0.25
     Fleming
    -0.24
    POSITIVE LOGITS
     source
    0.44
    æºIJ
    0.39
     structure
    0.39
    source
    0.38
    	source
    0.36
    ç»ĵæŀĦ
    0.36
     Source
    0.36
    _structure
    0.35
    structure
    0.35
    Structure
    0.34
    Activations Density 18.979%

    No Known Activations