© 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. 19-TRANSCODER-HP
    7. 8924
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çļĦåĵģçīĮ
    -0.28
    éĽĨåĽ¢èĤ¡ä»½
    -0.27
    缸è¿ij
    -0.27
     *</
    -0.26
     repr
    -0.25
    æĶ¸
    -0.25
    ylv
    -0.25
    heimer
    -0.25
    AKER
    -0.25
    å®ŀ践活åĬ¨
    -0.25
    POSITIVE LOGITS
    è¶ħ
    0.26
     catch
    0.26
    详æĥħ
    0.25
     exc
    0.24
    åİŁåĽł
    0.24
     sup
    0.24
    ileo
    0.24
    è¶ħ级
    0.24
     unlikely
    0.24
    etic
    0.23
    Activations Density 0.002%

    No Known Activations