© 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. 24-TRANSCODER-HP
    7. 150139
    Prev
    Next
    INDEX
    Explanations

    IA

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diss
    -0.29
     Outline
    -0.26
    æ±
    -0.25
    ή
    -0.25
    кли
    -0.25
    ä¹İ
    -0.25
     ad
    -0.24
    åī¯å¸Ĥéķ¿
    -0.24
    co
    -0.24
    oco
    -0.23
    POSITIVE LOGITS
    -display
    0.28
    annotations
    0.26
    鸾
    0.25
    æ´¼
    0.25
    ameda
    0.25
    .IP
    0.25
    roid
    0.25
    è¾Ł
    0.24
    -leg
    0.24
    Entr
    0.23
    Activations Density 1.415%

    No Known Activations