© 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. 12-TRANSCODER-HP
    7. 22753
    Prev
    Next
    INDEX
    Explanations

    Formal submissions and filings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ndl
    -0.28
    æī¹ç¤º
    -0.28
    ingroup
    -0.27
    亲èĩª
    -0.26
    éĤº
    -0.25
    /epl
    -0.25
    温馨æıIJ示
    -0.24
     timestep
    -0.24
    éĥ¦
    -0.23
    ItemId
    -0.23
    POSITIVE LOGITS
    ä¸ī级
    0.31
    iate
    0.29
    ase
    0.28
    iated
    0.27
    scr
    0.26
    ionario
    0.26
    lesi
    0.26
    nie
    0.26
    ony
    0.26
    oren
    0.25
    Activations Density 0.002%

    No Known Activations