© 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. 150382
    Prev
    Next
    INDEX
    Explanations

    before

    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
    Await
    -0.25
    æĮ£
    -0.24
    åĨħ
    -0.24
    upos
    -0.24
    åĪ°å¤Ħ
    -0.23
    åĮħåĽ´
    -0.23
    hall
    -0.23
    éĤ£äºĽ
    -0.23
    ienia
    -0.23
    หาย
    -0.23
    POSITIVE LOGITS
    ENCY
    0.28
    Descri
    0.24
    è°ĥåij³
    0.24
    QE
    0.23
     weigh
    0.23
    SYS
    0.23
     диаг
    0.23
    åħ¥å¸Ĥ
    0.23
     FormControl
    0.23
    Ĭ¶æĢģ
    0.23
    Activations Density 0.902%

    No Known Activations