© 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. 23-TRANSCODER-HP
    7. 23872
    Prev
    Next
    INDEX
    Explanations

    Code/license-related text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pn
    -0.28
    -cn
    -0.25
     race
    -0.25
    иÑĤелÑĮн
    -0.24
    åħ
    -0.24
    Ð¡ÐŁ
    -0.24
    LN
    -0.24
    ÙĪرد
    -0.24
     domestic
    -0.24
     conte
    -0.23
    POSITIVE LOGITS
     Scrolls
    0.26
    scroll
    0.26
    utes
    0.26
    bert
    0.25
    istes
    0.24
     womb
    0.24
    åı¯èĥ½åĩºçİ°
    0.24
    å±IJ
    0.24
    æľįåĬ¡æ°´å¹³
    0.24
     pomocÄħ
    0.24
    Activations Density 0.022%

    No Known Activations