Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 30-TRANSCODER-HP
    4. 15221
    Prev
    Next
    INDEX
    Explanations

    ichi

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erset
    -0.28
    -Origin
    -0.26
    Outline
    -0.26
    appen
    -0.26
    त
    -0.26
     fiber
    -0.25
     sl
    -0.25
     cud
    -0.25
    urat
    -0.25
     rest
    -0.24
    POSITIVE LOGITS
    ichi
    0.28
     kre
    0.27
    åı¤èĢģ
    0.26
    quina
    0.26
     nowhere
    0.25
    æIJŀç¬ij
    0.25
    longleftrightarrow
    0.24
     councils
    0.24
     instantaneous
    0.24
     newArr
    0.24
    Activations Density 0.002%

    No Known Activations