© 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. 25216
    Prev
    Next
    INDEX
    Explanations

    C/C++ preprocessor directives

    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
    åİĨ
    -0.28
    åİŁåĪĽ
    -0.27
    lf
    -0.26
     fé
    -0.26
    æŃ·
    -0.25
    åijĬè¯īä½ł
    -0.25
     Confeder
    -0.25
    å½ķ
    -0.24
    instance
    -0.24
    lk
    -0.24
    POSITIVE LOGITS
     curiosity
    0.47
     curious
    0.40
    çļĦéľĢæ±Ĥ
    0.37
    好å¥ĩ
    0.37
    æľīå¿ħè¦ģ
    0.35
    æĦıåĽ¾
    0.33
     craving
    0.32
     motivated
    0.32
    éľĢæ±Ĥ
    0.32
     Interested
    0.31
    Activations Density 0.001%

    No Known Activations