© 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. 30-TRANSCODER-HP
    7. 96520
    Prev
    Next
    INDEX
    Explanations

    natural selection, evolution

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _processes
    -0.27
    çĶŁçIJĨ
    -0.27
    ceeded
    -0.27
    æħ¢
    -0.26
    ilmiÅŁ
    -0.26
    ungi
    -0.25
    _sequences
    -0.25
    iox
    -0.25
    licas
    -0.24
    ([...
    -0.24
    POSITIVE LOGITS
     action
    0.33
    bell
    0.31
    act
    0.29
    -action
    0.29
    _action
    0.28
    action
    0.28
     brake
    0.27
     sculpt
    0.27
     acted
    0.27
    acting
    0.27
    Activations Density 0.110%

    No Known Activations