© 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. 33-TRANSCODER-HP
    7. 54200
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĶ¶åĽŀ
    -0.29
    -pill
    -0.29
    åıijåŀĭ
    -0.28
    è½±
    -0.24
    ntag
    -0.24
    Stub
    -0.24
    /MM
    -0.24
    ç»ıæŁ¥
    -0.24
    виÑĤ
    -0.23
    MMC
    -0.23
    POSITIVE LOGITS
     trusts
    0.28
    èĤ©
    0.26
    oad
    0.25
    g
    0.25
    ãĤ¤ãĥ³
    0.24
    è£ħ
    0.24
     affid
    0.24
    lane
    0.23
    che
    0.23
    æ³ķåĪĻ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.