© 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. 57604
    Prev
    Next
    INDEX
    Explanations

    code/unrecognized characters

    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
    ulan
    -0.31
    è·¯è¿ĩ
    -0.30
    è¿Ľåĩºåı£
    -0.28
    hal
    -0.26
    qn
    -0.26
    andbox
    -0.26
    è°ĥæŁ¥
    -0.25
    ula
    -0.25
    审åĪ¤
    -0.24
    审议
    -0.24
    POSITIVE LOGITS
    åĭ¤å¥ĭ
    0.28
    cratch
    0.27
    Stick
    0.27
    åĪ»èĭ¦
    0.27
    é£ŀæī¬
    0.26
    笮
    0.26
     Clim
    0.25
     SIGNAL
    0.25
    ä¿¡åı·
    0.24
    端æŃ£
    0.24
    Activations Density 0.002%

    No Known Activations