© 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. 98186
    Prev
    Next
    INDEX
    Explanations

    Code and math equations

    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
    arde
    -0.25
    åĵĦ
    -0.25
    æ±ģ
    -0.24
    çĹ¹
    -0.24
     twitch
    -0.24
    ä¸ĬçļĦ
    -0.23
     twice
    -0.23
    FORCE
    -0.23
    arpa
    -0.23
    åķĨ
    -0.23
    POSITIVE LOGITS
     Hands
    0.26
    PP
    0.25
    LEV
    0.25
    çļ®
    0.25
    (++
    0.24
    pp
    0.24
     Bath
    0.23
    åłª
    0.23
    æīĭ
    0.23
     genders
    0.23
    Activations Density 0.026%

    No Known Activations