© 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. 23-TRANSCODER-HP
    7. 24182
    Prev
    Next
    INDEX
    Explanations

    Prepositions and conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    貨
    -0.28
    è´§
    -0.27
     twentieth
    -0.26
    åı¦ä¸Ģ个
    -0.26
    å§ij
    -0.26
    港åĮº
    -0.26
    çĻ¾åĪĨä¹ĭ
    -0.26
    .minecraft
    -0.25
    .runner
    -0.25
     pat
    -0.24
    POSITIVE LOGITS
    ä¹ĥ
    0.28
     dru
    0.28
    åĴ¸
    0.26
    æĻ¤
    0.26
    ikal
    0.26
    é£İåı£
    0.26
    çŁ³æ¦´
    0.26
    signature
    0.25
    ä¸įéĢļ
    0.25
     Flux
    0.24
    Activations Density 0.001%

    No Known Activations