© 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. 25116
    Prev
    Next
    INDEX
    Explanations

    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
    дав
    -0.27
    mar
    -0.26
    éħį
    -0.26
    даеÑĤÑģÑı
    -0.25
     Pru
    -0.25
    _serializer
    -0.24
    pare
    -0.24
    建ç«ĭ
    -0.24
     Hari
    -0.24
     doubt
    -0.24
    POSITIVE LOGITS
     indiv
    0.28
    æ¨ĺ
    0.28
    aviest
    0.26
    使çĶ¨èĢħæĪĸ
    0.25
    );\↵
    0.25
     immedi
    0.25
    æŁ©
    0.24
    æĹ¥è®¯
    0.24
    å¾Īä½İ
    0.24
    ãĥ¡ãĥªãĥĥãĥĪ
    0.24
    Activations Density 0.001%

    No Known Activations