© 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. 9046
    Prev
    Next
    INDEX
    Explanations

    from

    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
    ç§ijåѦ
    -0.32
    úc
    -0.30
    orama
    -0.27
     evidence
    -0.26
    Uri
    -0.26
    çŁ¿çī©è´¨
    -0.25
     оÑĢг
    -0.25
     pos
    -0.25
     posit
    -0.24
    UIT
    -0.24
    POSITIVE LOGITS
    è¡°
    0.29
    æģ°
    0.28
    æįķ
    0.27
    åĪį
    0.26
    éĺħ
    0.26
    eder
    0.26
    ãĥĸãĥ«
    0.25
    ocket
    0.25
    nown
    0.25
    åħ´èĩ´
    0.25
    Activations Density 0.007%

    No Known Activations