© 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. 111436
    Prev
    Next
    INDEX
    Explanations

    positive sentiment

    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
     interviews
    -0.29
    erview
    -0.28
    ãĤĴæ±ĤãĤģ
    -0.26
     Interviews
    -0.26
    listeners
    -0.25
    /MM
    -0.24
     LZ
    -0.24
    ause
    -0.23
    顶
    -0.23
    asher
    -0.23
    POSITIVE LOGITS
    ä¹Łä¸º
    0.28
    ä¹Łä¸į
    0.27
    ä¹Łè¦ģ
    0.26
    ÄŁ
    0.25
    èĴĻ
    0.24
    ç»ıå¼Ģ
    0.24
    亦
    0.24
    mw
    0.24
    !(
    0.24
    ---↵
    0.23
    Activations Density 0.009%

    No Known Activations