© 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. 25-TRANSCODER-HP
    7. 108375
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĪĸåħ¶ä»ĸ
    -0.38
    åħ¶å®ĥ
    -0.38
    åħ¶ä»ĸ人
    -0.37
    åħ¶ä»ĸ
    -0.33
    -other
    -0.31
    çĽ¸ä¼¼
    -0.31
    åıĬåħ¶ä»ĸ
    -0.30
    OTHER
    -0.29
    (other
    -0.29
     otros
    -0.29
    POSITIVE LOGITS
     the
    0.29
     a
    0.28
     immediate
    0.26
    次è¦ģ
    0.26
     either
    0.26
     der
    0.25
     secondary
    0.25
     Lesser
    0.25
     Were
    0.25
     Matters
    0.24
    Activations Density 0.913%

    No Known Activations