© 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. 18-TRANSCODER-HP
    7. 88883
    Prev
    Next
    INDEX
    Explanations

    End of texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     minLength
    -0.27
    ITIVE
    -0.26
    aida
    -0.26
    uckle
    -0.25
    =pos
    -0.24
    车ä¸Ĭ
    -0.24
    å·¥ä½ľæĢ»ç»ĵ
    -0.24
    eeper
    -0.24
    çļĦç¡®
    -0.24
    gradable
    -0.24
    POSITIVE LOGITS
    æľ¬éĴ±
    0.29
    -round
    0.27
    è¿ŀèĥľ
    0.26
     costing
    0.26
    Robin
    0.25
    .span
    0.25
    ipop
    0.24
    æĭ¬
    0.24
    spacing
    0.24
    á»Ŀi
    0.24
    Activations Density 20.332%

    No Known Activations