© 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. 43555
    Prev
    Next
    INDEX
    Explanations

    to

    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
    åĮħæĭ¬
    -0.28
     incl
    -0.28
    æķĪåºĶ
    -0.27
    åĪ°äºĨ
    -0.26
    UserRole
    -0.26
    èĩ³
    -0.26
    -Sah
    -0.26
    to
    -0.25
    èĩ³ä¸Ĭ
    -0.25
     to
    -0.24
    POSITIVE LOGITS
     not
    0.43
     Not
    0.35
    not
    0.34
     NOT
    0.33
    Not
    0.31
    (not
    0.30
     be
    0.30
    NOT
    0.30
    .NOT
    0.28
     want
    0.27
    Activations Density 0.009%

    No Known Activations