© 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. 88588
    Prev
    Next
    INDEX
    Explanations

    believe/think

    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
    ãĥ¥ãĥ¼
    -0.30
    èĪįä¸įå¾Ĺ
    -0.27
    代价
    -0.27
    绣çŃ¹æİ¨è¿Ľ
    -0.26
     Cush
    -0.26
    Manufacturer
    -0.26
    è½®
    -0.25
    åĽ½å®¶å®īåħ¨
    -0.24
    Otherwise
    -0.24
    WithEmail
    -0.24
    POSITIVE LOGITS
    cade
    0.29
    åĪ«
    0.27
     happily
    0.25
    jian
    0.25
    bij
    0.25
    åľ¨äºİ
    0.25
    ampoline
    0.25
    isors
    0.24
    令
    0.24
     signature
    0.24
    Activations Density 0.016%

    No Known Activations