© 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. 30-TRANSCODER-HP
    7. 96552
    Prev
    Next
    INDEX
    Explanations

    Legal and numerical references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     derivative
    -0.31
    grand
    -0.28
    der
    -0.26
    ä¾Ħ
    -0.25
     mort
    -0.25
    peak
    -0.25
    ä»Ħ
    -0.25
    esso
    -0.24
     grandson
    -0.24
    ipi
    -0.24
    POSITIVE LOGITS
    æ®ĸæ°ij
    0.27
    emento
    0.26
    å°ıå§IJ
    0.24
     Lon
    0.24
    listen
    0.24
    Living
    0.24
    Lon
    0.23
    ç»
    0.23
    idth
    0.23
    åªĴ
    0.23
    Activations Density 0.882%

    No Known Activations