© 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. 98132
    Prev
    Next
    INDEX
    Explanations

    Function

    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
    Nr
    -0.40
    èį·åħ°
    -0.38
     Danish
    -0.37
    çijŀåħ¸
    -0.37
    èķ²
    -0.36
    -/
    -0.35
     Dutch
    -0.34
    å¥¥åľ°åĪ©
    -0.34
     Copenhagen
    -0.34
     Johannes
    -0.33
    POSITIVE LOGITS
     Tome
    0.30
     дем
    0.28
    沿
    0.25
    ilor
    0.25
    Doug
    0.25
    пÑĥÑģÑĤ
    0.24
    åľ¨è¿ĩ渡
    0.24
    çĥĥ
    0.24
    orio
    0.23
    ÑĮÑİ
    0.23
    Activations Density 0.012%

    No Known Activations