© 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. 22-TRANSCODER-HP
    7. 111898
    Prev
    Next
    INDEX
    Explanations

    fruits and nuts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å±Ī
    -0.27
     procur
    -0.26
     such
    -0.26
    such
    -0.25
    into
    -0.25
    åħĪè¿Ľ
    -0.25
     critically
    -0.25
    su
    -0.25
     uniquely
    -0.25
    &
    -0.24
    POSITIVE LOGITS
    ","",
    0.26
     *__
    0.25
     Kore
    0.25
    è´¬åĢ¼
    0.24
     treeNode
    0.24
    æĢĢæĬ±
    0.24
    ollah
    0.23
    WISE
    0.23
    TION
    0.23
     <",
    0.23
    Activations Density 0.043%

    No Known Activations