© 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. 9-TRANSCODER-HP
    7. 29556
    Prev
    Next
    INDEX
    Explanations

    L

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gage
    -0.28
    -conf
    -0.28
    è¿ĩå¾Ģ
    -0.27
    gé
    -0.26
    ges
    -0.26
    packed
    -0.26
    ioneer
    -0.25
     laps
    -0.25
    emory
    -0.25
     unfolded
    -0.24
    POSITIVE LOGITS
    quat
    0.33
    rieve
    0.29
     Britt
    0.29
    catch
    0.26
    око
    0.25
    	catch
    0.25
     Witness
    0.24
    ç¼ļ
    0.24
    ielding
    0.24
    åĩ«
    0.24
    Activations Density 0.828%

    No Known Activations