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. 43901
    Prev
    Next
    INDEX
    Explanations

    hidden

    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
     \'
    -0.07
    双十一
    -0.07
     Tess
    -0.07
     });↵↵↵↵
    -0.07
     '.
    -0.07
     شب
    -0.06
    bi
    -0.06
    producto
    -0.06
    ph
    -0.06
     massive
    -0.06
    POSITIVE LOGITS
     RESET
    0.08
    候选人
    0.07
     programmer
    0.07
     своего
    0.07
    一起装修
    0.07
     Peanut
    0.07
    农贸
    0.07
    坚果
    0.07
    него
    0.07
    圢
    0.07
    Activations Density 0.002%

    No Known Activations