© 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. 24752
    Prev
    Next
    INDEX
    Explanations

    algae

    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
    éĢı
    -0.27
    appa
    -0.26
    è¿Ļ次
    -0.25
    æľ«ç«¯
    -0.25
    æ¯ıèĤ¡
    -0.25
    sig
    -0.25
    å®Ī
    -0.25
    åī¯ä¸»ä»»
    -0.24
    alty
    -0.24
    rade
    -0.24
    POSITIVE LOGITS
    asions
    0.25
    ectors
    0.25
     okre
    0.24
    çłĤ
    0.24
     boats
    0.24
    ->__
    0.24
    fos
    0.24
    並å°ĩ
    0.23
    eci
    0.23
    	DECLARE
    0.23
    Activations Density 0.038%

    No Known Activations