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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 129659
    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
     nuisance
    -0.07
     Lexus
    -0.07
    /etc
    -0.07
    (pg
    -0.07
    🥨
    -0.07
    \Entity
    -0.07
     café
    -0.06
    ��
    -0.06
     prom
    -0.06
    Wis
    -0.06
    POSITIVE LOGITS
    筹建
    0.07
    嫕
    0.06
    最受
    0.06
     ARC
    0.06
    얕
    0.06
    襞
    0.06
     dom
    0.06
    非常适合
    0.06
     interruptions
    0.06
     BET
    0.06
    Activations Density 0.001%

    No Known Activations