© 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. 18847
    Prev
    Next
    INDEX
    Explanations

    genetic/genomic

    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
    åĩĿ
    -0.30
    ç´¯
    -0.27
    blind
    -0.25
    egr
    -0.25
    æł¸
    -0.24
    avored
    -0.24
    OLF
    -0.24
    _UPLOAD
    -0.24
    descriptor
    -0.23
    geb
    -0.23
    POSITIVE LOGITS
     instability
    0.29
     sá»Ńa
    0.28
     unstable
    0.27
    Inst
    0.26
    ansom
    0.26
    anian
    0.26
    ksam
    0.26
    ortho
    0.26
    _inst
    0.25
     irres
    0.25
    Activations Density 1.097%

    No Known Activations