© 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. 53074
    Prev
    Next
    INDEX
    Explanations

    Chromatography/Spectrometry

    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
    è°IJ
    -0.28
     jo
    -0.27
     Epid
    -0.26
    æŁ¬
    -0.26
     dess
    -0.25
     interruption
    -0.25
     Ep
    -0.25
    ijľ
    -0.24
    olta
    -0.24
    ÑĢак
    -0.24
    POSITIVE LOGITS
     H
    0.57
    èµµ
    0.46
    H
    0.43
    _H
    0.42
    é«ĺæķĪ
    0.40
    è¶Ļ
    0.39
    èī²
    0.36
    液
    0.35
    æ°Ķè´¨
    0.34
    _h
    0.33
    Activations Density 0.491%

    No Known Activations