© 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. 31-TRANSCODER-HP
    7. 18897
    Prev
    Next
    INDEX
    Explanations

    are

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     done
    -0.38
    .done
    -0.29
    done
    -0.28
    Ñĩем
    -0.27
    	done
    -0.27
     channelId
    -0.27
    RuleContext
    -0.27
     wholesale
    -0.26
    -done
    -0.26
    æĻı
    -0.26
    POSITIVE LOGITS
    èĩªçĶ±
    0.33
     cord
    0.29
     freely
    0.29
    èī¯å¥½
    0.28
     vet
    0.28
     free
    0.26
    åĪ°
    0.25
     WITHOUT
    0.25
    ç»Ħ
    0.25
     fre
    0.24
    Activations Density 0.015%

    No Known Activations