© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5845
    Prev
    Next
    INDEX
    Explanations

    Grammatical filler words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĨį
    -0.30
     trail
    -0.28
     Trail
    -0.27
    çĬ¹
    -0.25
    ût
    -0.25
    fraction
    -0.24
    åĨįåİ»
    -0.24
    æħ¢
    -0.24
    thag
    -0.24
    è¶Ĭ
    -0.24
    POSITIVE LOGITS
    侧éĿ¢
    0.29
     Haley
    0.27
     plates
    0.26
    åı¦ä¸Ģè¾¹
    0.26
    amin
    0.25
    æ·±å±Ĥ
    0.25
    ç¨Ķ
    0.25
     abund
    0.23
    两åıª
    0.23
     ears
    0.23
    Activations Density 0.307%

    No Known Activations