© 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. 57888
    Prev
    Next
    INDEX
    Explanations

    professional organizations/standards

    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
    exter
    -0.29
     disciplines
    -0.27
    seg
    -0.26
     resc
    -0.26
    sea
    -0.26
    ensis
    -0.25
     Blazers
    -0.25
    åĿıäºĨ
    -0.25
    æķijæ²»
    -0.24
     Grim
    -0.24
    POSITIVE LOGITS
    Ret
    0.25
     oc
    0.25
    åī¯ä¹¦è®°
    0.25
    ÑģÑĤв
    0.24
    @Component
    0.24
    åħī
    0.23
    âĪ¨
    0.23
    uet
    0.23
    ıs
    0.23
    .perform
    0.23
    Activations Density 0.002%

    No Known Activations