© 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. 98142
    Prev
    Next
    INDEX
    Explanations

    Commas, "I"

    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
     strugg
    -0.28
    è¿ľæĸ¹
    -0.26
    atory
    -0.25
    ATORY
    -0.23
     Voices
    -0.23
    annis
    -0.23
    åģļä¸Ģ个
    -0.23
    çĩİ
    -0.23
    ÂŃs
    -0.23
    ainless
    -0.23
    POSITIVE LOGITS
    ä¸įå¦Ĥ
    0.31
    ç»ĵ论
    0.30
    以为
    0.29
    æĪij认为
    0.26
     sue
    0.26
    认为
    0.26
    æĪij以为
    0.25
    äºĴ
    0.24
    fore
    0.24
     conclusion
    0.24
    Activations Density 0.025%

    No Known Activations