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. 130737
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    لة
    -0.07
    od
    -0.07
    累累
    -0.07
    idente
    -0.07
     Declare
    -0.07
    ǝ
    -0.07
    .high
    -0.06
     bà
    -0.06
    タン
    -0.06
    tod
    -0.06
    POSITIVE LOGITS
    focused
    0.08
     downfall
    0.07
     Likes
    0.07
     purification
    0.07
    ]'↵
    0.07
    ꅉ
    0.07
    重点工作
    0.07
     העיר
    0.07
    معالجة
    0.07
    עשייה
    0.07
    Activations Density 0.003%

    No Known Activations