© 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. 40123
    Prev
    Next
    INDEX
    Explanations

    flat/flatten

    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
    ç¯ĵ
    -0.29
    è§ĤéŁ³
    -0.25
    è¾ĵåĩº
    -0.24
    teness
    -0.24
    èĪ
    -0.24
    еÑģÑĤв
    -0.24
    opleft
    -0.24
     vidéos
    -0.24
    æĶ¾æĿ¾
    -0.23
    说æĺ¯
    -0.23
    POSITIVE LOGITS
    vince
    0.29
    -gap
    0.27
    oft
    0.25
    å¾Ģåīį
    0.24
    _ACL
    0.24
    éĥ¨åĪĨåľ°åĮº
    0.23
    UCK
    0.23
    .ser
    0.23
    _HIT
    0.23
    Vectors
    0.23
    Activations Density 0.191%

    No Known Activations