© 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. 23890
    Prev
    Next
    INDEX
    Explanations

    comparative

    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
    ä¸ĢåĪ»
    -0.27
    hints
    -0.25
    eced
    -0.25
     lend
    -0.25
    ioni
    -0.25
     ]).
    -0.24
     }):
    -0.24
     filetype
    -0.24
    nowrap
    -0.24
    iene
    -0.24
    POSITIVE LOGITS
     micro
    0.26
    å¼¹
    0.26
    .fm
    0.26
    ä½łæĺ¯
    0.26
     Micro
    0.26
    ÑģÑĤÑĢой
    0.25
    .getPath
    0.25
     Usually
    0.25
    micro
    0.24
    æĭĤ
    0.24
    Activations Density 0.002%

    No Known Activations