© 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. 14-TRANSCODER-HP
    7. 41306
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    burger
    -0.27
    tone
    -0.25
    æĮĤéĴ©
    -0.25
    gene
    -0.24
    ibly
    -0.24
    ear
    -0.24
    ibilidad
    -0.23
    çħĬ
    -0.23
    èĤĵ
    -0.23
     crop
    -0.23
    POSITIVE LOGITS
    posix
    0.26
    %'↵
    0.26
    çĻ½é©¬
    0.25
    ÑĮÑı
    0.25
    温æļĸ
    0.25
    __',
    0.25
    ',{'
    0.25
    %',
    0.24
    ä½ĵéĩį
    0.23
    æ¶Ī
    0.23
    Activations Density 0.342%

    No Known Activations