© 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. 57540
    Prev
    Next
    INDEX
    Explanations

    electro or uro

    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
    iesta
    -0.29
     fully
    -0.28
    ueling
    -0.27
     perfectly
    -0.26
    å¸ĤæĶ¿åºľ
    -0.24
    åĮ»ç§ij大åѦ
    -0.24
    iciary
    -0.24
     aff
    -0.24
    ItemImage
    -0.24
    advertisement
    -0.24
    POSITIVE LOGITS
    ary
    0.28
    enga
    0.28
    Av
    0.28
    odes
    0.26
    CR
    0.26
    ·
    0.26
    æ¾ľ
    0.26
    ode
    0.26
    ent
    0.26
    eva
    0.25
    Activations Density 1.097%

    No Known Activations