© 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. 150250
    Prev
    Next
    INDEX
    Explanations

    CB

    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
    leground
    -0.28
    elapsed
    -0.27
    -fw
    -0.27
     Decomp
    -0.26
    æ±Łä¸ľ
    -0.25
    æ¼Ĥæµģ
    -0.25
    ade
    -0.24
    ewidth
    -0.24
    haps
    -0.24
    which
    -0.24
    POSITIVE LOGITS
     while
    0.28
     pe
    0.28
     AND
    0.27
     wax
    0.27
    ä¸į失
    0.26
     Wax
    0.26
     DAC
    0.26
    ileo
    0.25
     with
    0.25
     +
    0.25
    Activations Density 5.643%

    No Known Activations