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. 130976
    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
    劂
    -0.08
    使之
    -0.07
    crime
    -0.07
    龠
    -0.07
     śmier
    -0.07
     Defence
    -0.07
    icine
    -0.07
    维修
    -0.07
    虬
    -0.07
     lives
    -0.07
    POSITIVE LOGITS
    ]-'
    0.08
    oauth
    0.07
    +=
    0.07
    بال
    0.07
    equals
    0.07
    )=>
    0.07
    taking
    0.07
    ://
    0.07
    -$
    0.07
     peer
    0.07
    Activations Density 0.005%

    No Known Activations