© 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. 42735
    Prev
    Next
    INDEX
    Explanations

    the

    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
    spect
    -0.30
    sig
    -0.30
     THEN
    -0.29
    ambi
    -0.28
    annel
    -0.28
    then
    -0.28
    ä¸įçĦ¶
    -0.26
    Then
    -0.26
     then
    -0.25
     entonces
    -0.25
    POSITIVE LOGITS
     immediately
    0.47
     immediate
    0.41
    ç«ĭåį³
    0.36
     Immediately
    0.34
     very
    0.32
    èµ·çĤ¹
    0.32
    Immediate
    0.32
     Very
    0.31
    mediately
    0.30
    Very
    0.30
    Activations Density 0.002%

    No Known Activations