© 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. 22-TRANSCODER-HP
    7. 87822
    Prev
    Next
    INDEX
    Explanations

    research papers and legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bane
    -0.27
    bal
    -0.26
    津贴
    -0.26
    -tax
    -0.25
    åıijå±ķæĪĺçķ¥
    -0.25
    -threat
    -0.25
    è¡¥åĬ©
    -0.24
    人éĹ´
    -0.24
     band
    -0.24
    abus
    -0.24
    POSITIVE LOGITS
    çݯèĬĤ
    0.32
    æĸ¹æ¡Ī
    0.25
     Gerry
    0.24
    ALLY
    0.24
     hop
    0.24
    éļ¾åħ³
    0.24
    æıIJæ¡Ī
    0.24
     sak
    0.24
    åī§æľ¬
    0.23
    æ¯ĭ
    0.23
    Activations Density 0.038%

    No Known Activations