© 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. 43221
    Prev
    Next
    INDEX
    Explanations

    chance, likelihood, possibility

    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
     Himself
    -0.30
    inel
    -0.28
     ourselves
    -0.28
    tant
    -0.27
    åľ¨ä¸Ĭæµ·
    -0.26
    æĬĬ她
    -0.26
    well
    -0.26
     Yourself
    -0.25
     myself
    -0.25
    æĬĬä»ĸ
    -0.24
    POSITIVE LOGITS
     they
    0.47
     of
    0.36
     critics
    0.35
    they
    0.33
     she
    0.32
     therapists
    0.31
     manufacturers
    0.29
     we
    0.29
    å½ĵåľ°äºº
    0.28
    _of
    0.28
    Activations Density 0.004%

    No Known Activations