© 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. 56948
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    [:,:,
    -0.27
    åħ¨ãģ¦
    -0.25
     (#
    -0.25
    :/
    -0.24
    ter
    -0.24
    æľīæķĪåľ°
    -0.23
    Machine
    -0.23
    ason
    -0.23
    好å¥ĩå¿ĥ
    -0.23
    座æ¤ħ
    -0.23
    POSITIVE LOGITS
     ank
    0.27
    ellaneous
    0.26
    trinsic
    0.26
    itize
    0.25
    advertisement
    0.25
    _kategori
    0.25
    itized
    0.24
    ackle
    0.24
    éĴĪ
    0.24
     annex
    0.24
    Activations Density 0.008%

    No Known Activations