© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 109655
    Prev
    Next
    INDEX
    Explanations

    Tree

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    某一
    -0.08
    .setMax
    -0.07
    Ⲁ
    -0.07
     môi
    -0.07
    ิ
    -0.07
    迸
    -0.07
    .AD
    -0.07
     intimidating
    -0.07
    悌
    -0.07
    成长为
    -0.07
    POSITIVE LOGITS
    Highlights
    0.07
    _COUNTRY
    0.07
    Hum
    0.07
     hitch
    0.06
    Moon
    0.06
    JT
    0.06
    quarters
    0.06
    Origin
    0.06
    ****
    0.06
    icontrol
    0.06
    Activations Density 0.000%

    No Known Activations