© 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. 8294
    Prev
    Next
    INDEX
    Explanations

    Programming / Code related

    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
     Eck
    -0.25
    \<
    -0.25
     */;↵
    -0.24
     dried
    -0.24
     Naturally
    -0.23
    jad
    -0.23
    jp
    -0.23
    ));//
    -0.23
     hardships
    -0.23
    uw
    -0.23
    POSITIVE LOGITS
    otent
    0.30
    åºķçĽĺ
    0.28
    cene
    0.28
     RVA
    0.27
    abol
    0.26
    Safety
    0.26
    artin
    0.25
     Safety
    0.25
     dialogRef
    0.25
    åħī
    0.24
    Activations Density 0.000%

    No Known Activations