© 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. 24-TRANSCODER-HP
    7. 150495
    Prev
    Next
    INDEX
    Explanations

    Percentages and statistics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ŃåĽ½ä¼ģä¸ļ
    -0.30
    æĹĹä¸ĭ
    -0.30
    éĽĨåĽ¢æĹĹä¸ĭ
    -0.28
    åģļäºĭ
    -0.27
     knitting
    -0.25
    åŃĹ
    -0.25
    çĽĬ
    -0.24
    Ñīей
    -0.24
    oken
    -0.24
    ODO
    -0.24
    POSITIVE LOGITS
     proportion
    0.33
    çļĦæ¯Ķä¾ĭ
    0.30
    æ¯Ķä¾ĭ
    0.29
    åįłæ¯Ķ
    0.26
     suppress
    0.24
    æ¯Ķéĩį
    0.24
     propor
    0.24
     ratio
    0.24
    centage
    0.24
    iface
    0.24
    Activations Density 0.957%

    No Known Activations