© 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. 149680
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Save
    -0.28
     salvation
    -0.28
     v
    -0.28
    æķij
    -0.28
     standard
    -0.28
     salv
    -0.27
     works
    -0.27
     universal
    -0.27
     undo
    -0.26
     or
    -0.26
    POSITIVE LOGITS
     Shooter
    0.32
    ·æĸ°
    0.28
    )arg
    0.26
    moid
    0.26
    	tests
    0.25
    noxious
    0.25
     pháºŃn
    0.25
    -playing
    0.25
    policy
    0.24
    $i
    0.24
    Activations Density 0.092%

    No Known Activations

    This feature has no known activations.