© 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. 25-TRANSCODER-HP
    7. 108322
    Prev
    Next
    INDEX
    Explanations

    golden

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħ³å¿ĥ
    -0.27
    to
    -0.26
     visual
    -0.25
     Visual
    -0.25
     concerned
    -0.24
    dl
    -0.24
    mana
    -0.24
     None
    -0.24
    visual
    -0.24
    alten
    -0.24
    POSITIVE LOGITS
    rô
    0.27
    åİŁåĽłæĺ¯
    0.27
    çIJĨçĶ±
    0.27
    terior
    0.24
    Ñĥв
    0.24
    morph
    0.24
    æĺ¶
    0.24
    IENTATION
    0.24
    finity
    0.24
    éĹªèĢĢ
    0.24
    Activations Density 1.061%

    No Known Activations