© 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. 27-TRANSCODER-HP
    7. 9093
    Prev
    Next
    INDEX
    Explanations

    Events and celebrations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hour
    -0.30
    gré
    -0.30
     particles
    -0.26
    éĺ´å½±
    -0.26
     minute
    -0.25
     col
    -0.25
     hour
    -0.25
    æĿłæĿĨ
    -0.25
    è¯ķåį·
    -0.25
    pp
    -0.24
    POSITIVE LOGITS
    hos
    0.29
    ****/↵
    0.28
     oslo
    0.27
    _cmds
    0.27
     Irma
    0.25
    xBC
    0.25
    IRS
    0.25
     preprocessing
    0.25
    饺åŃIJ
    0.24
     prere
    0.24
    Activations Density 0.002%

    No Known Activations