© 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. 23-TRANSCODER-HP
    7. 25128
    Prev
    Next
    INDEX
    Explanations

    confident

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <Field
    -0.27
    oshi
    -0.27
    iska
    -0.27
    æī
    -0.26
    æľīæŶ
    -0.25
    onest
    -0.25
    çĶļèĩ³
    -0.25
    çŁŃæľŁåĨħ
    -0.24
    one
    -0.24
    ioni
    -0.24
    POSITIVE LOGITS
     Birch
    0.26
    aneously
    0.25
    ness
    0.25
     Cic
    0.25
     Beer
    0.24
     à¹Ĩ
    0.24
    mente
    0.24
    NESS
    0.24
    pyx
    0.24
    idade
    0.23
    Activations Density 0.025%

    No Known Activations