© 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. 41893
    Prev
    Next
    INDEX
    Explanations

    Words ending in "ic(s)"

    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
    ãĥ©ãĥ³ãĤ¹
    -0.23
     xen
    -0.23
    èµĽ
    -0.23
    CEED
    -0.23
    .foundation
    -0.22
    äºĭä¸ļåıijå±ķ
    -0.22
    iative
    -0.22
    anoi
    -0.22
    æī¼
    -0.22
    ady
    -0.22
    POSITIVE LOGITS
    ics
    1.08
    ical
    1.02
    ik
    1.02
    ically
    1.00
    ica
    0.95
    icos
    0.92
    ico
    0.91
     ic
    0.90
    icas
    0.89
    ic
    0.87
    Activations Density 0.045%

    No Known Activations