© 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. 32-TRANSCODER-HP
    7. 41320
    Prev
    Next
    INDEX
    Explanations

    fl

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wap
    -0.33
    空æ°Ķ
    -0.30
     Pence
    -0.28
    Recovered
    -0.24
    pte
    -0.23
    Cr
    -0.23
    æ±ģ
    -0.23
    åĺĺ
    -0.23
    except
    -0.23
     Upper
    -0.23
    POSITIVE LOGITS
    enticator
    0.29
    eter
    0.25
     retro
    0.25
    tica
    0.25
    ider
    0.24
    åŀĴ
    0.24
    _INITIALIZER
    0.24
     Spect
    0.24
    back
    0.23
    جاÙĦ
    0.23
    Activations Density 0.005%

    No Known Activations