Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 71650
    Prev
    Next
    INDEX
    Explanations

    System calls and constants

    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
     kịp
    -0.08
    lette
    -0.07
    castHit
    -0.07
    باك
    -0.07
     Barack
    -0.07
     أمام
    -0.07
    뮬
    -0.07
    뎃
    -0.06
    戣
    -0.06
    立法
    -0.06
    POSITIVE LOGITS
    נק
    0.08
     sis
    0.07
    指着
    0.07
     Sheffield
    0.07
    _pay
    0.07
    .bold
    0.07
     assembling
    0.07
     stim
    0.07
     sg
    0.07
    低下
    0.07
    Activations Density 0.007%

    No Known Activations