© 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. 33-TRANSCODER-HP
    7. 53911
    Prev
    Next
    INDEX
    Explanations

    named entities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æīįè¡Į
    -0.35
    å°±åı¯ä»¥äºĨ
    -0.31
    äºĨåIJ§
    -0.30
    èĢĮä¸įæĺ¯
    -0.30
    åĨįåĪ°
    -0.30
    precedented
    -0.29
    ä¸ºæł¸å¿ĥçļĦ
    -0.29
    è¿Ļæīįæĺ¯
    -0.29
    没åħ³ç³»
    -0.29
    çŃīä¸Ģç³»åĪĹ
    -0.29
    POSITIVE LOGITS
     decided
    0.50
     uses
    0.48
     considers
    0.46
     started
    0.46
     wants
    0.45
     claims
    0.45
     decides
    0.44
     leaned
    0.44
     suffered
    0.44
     insists
    0.43
    Activations Density 1.646%

    No Known Activations