© 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. 111953
    Prev
    Next
    INDEX
    Explanations

    delimiters

    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
    æĹ¢è¦ģ
    -0.28
    á»ģn
    -0.27
     Affero
    -0.26
     glands
    -0.24
    ’Brien
    -0.24
     electrode
    -0.24
    zeug
    -0.24
    олод
    -0.23
    ä¸Ģ对
    -0.23
    etable
    -0.23
    POSITIVE LOGITS
    èĩªçĦ¶ç§ijåѦ
    0.27
    asl
    0.26
    enti
    0.25
    uracy
    0.25
     Jr
    0.25
    دÙĤ
    0.24
     coraz
    0.23
    æĦıåĽ¾
    0.23
    CRT
    0.23
    å§ĭ
    0.23
    Activations Density 0.004%

    No Known Activations