© 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. 25109
    Prev
    Next
    INDEX
    Explanations

    Laws/Acts of government

    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
    æ®·
    -0.27
    BUR
    -0.26
    é¤IJ
    -0.26
     UNUSED
    -0.25
    rien
    -0.25
     #%
    -0.24
     orient
    -0.24
     adventure
    -0.24
    å¼ĺ
    -0.23
    æķĻçłĶ
    -0.23
    POSITIVE LOGITS
    æ³ķè§Ħ
    0.32
     legally
    0.29
     legal
    0.29
    æ³ķåĪ¶
    0.28
     regulation
    0.28
     aimed
    0.28
     laws
    0.27
    æī§æ³ķ
    0.26
    omy
    0.26
    æ³ķ令
    0.26
    Activations Density 0.004%

    No Known Activations