© 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. 41758
    Prev
    Next
    INDEX
    Explanations

    say time units

    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
    hab
    -0.31
    él
    -0.30
    etermined
    -0.28
    åħŃå¹´
    -0.27
    ud
    -0.27
    mont
    -0.24
    lian
    -0.24
     integr
    -0.24
    èij©
    -0.24
    hai
    -0.24
    POSITIVE LOGITS
    earing
    0.28
     race
    0.27
     sessions
    0.26
     valide
    0.26
    sessions
    0.25
    ç§įæĹı
    0.25
    é¾Ħ
    0.25
    çļĦç¼ĺæķħ
    0.25
    泡沫
    0.25
     pumping
    0.24
    Activations Density 0.001%

    No Known Activations