© 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. 14-TRANSCODER-HP
    7. 40275
    Prev
    Next
    INDEX
    Explanations

    academic/scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gov
    -0.28
    _DETECT
    -0.27
    -gen
    -0.27
    +$
    -0.27
    åij¢
    -0.26
    UCCEEDED
    -0.26
    $$$$
    -0.26
    è¯Ħ级
    -0.24
    dna
    -0.24
    -det
    -0.24
    POSITIVE LOGITS
    erto
    0.28
    umo
    0.24
    æ¿ĢåĬ±
    0.24
    深交
    0.23
    oucher
    0.23
    ucha
    0.23
    Cum
    0.23
    ertype
    0.23
     boy
    0.23
    mare
    0.23
    Activations Density 1.889%

    No Known Activations