© 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. 23796
    Prev
    Next
    INDEX
    Explanations

    but not

    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
    åĬŀ
    -0.28
    æŶéĹ´åĴĮ
    -0.27
     Hughes
    -0.26
    æĢģ
    -0.26
    åĪ¶éĢł
    -0.26
    è°Ľ
    -0.26
    å±Ĭ
    -0.26
     lle
    -0.25
    侧éĿ¢
    -0.24
    åĪ¶ä½ľ
    -0.24
    POSITIVE LOGITS
    åĮħ容
    0.27
    æŶä¸į
    0.26
    olu
    0.26
    umar
    0.25
    _UNITS
    0.25
    éĩįè¦ģçļĦ
    0.25
    shal
    0.24
    å®ŀçĶ¨
    0.24
    ä½ĨæĪij们
    0.24
    éĢĦ
    0.23
    Activations Density 0.020%

    No Known Activations