© 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. 8645
    Prev
    Next
    INDEX
    Explanations

    Districts, predictions, technical questions

    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
     Singer
    -0.28
    ä¸įå°½
    -0.27
    alous
    -0.26
    evin
    -0.26
    å¥īçĮ®
    -0.26
    -fw
    -0.25
    å¯ĩ
    -0.25
    åħĪ导
    -0.25
    -ranging
    -0.25
    (tol
    -0.24
    POSITIVE LOGITS
    enty
    0.31
    imo
    0.29
     clin
    0.29
    ICES
    0.27
     algorithm
    0.26
    å¢ŀéĢŁ
    0.26
    ä½£éĩij
    0.26
    hä
    0.26
    clave
    0.26
    åĪĨè£Ĥ
    0.25
    Activations Density 0.002%

    No Known Activations