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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 129755
    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
    拿了
    -0.08
     Honolulu
    -0.07
    שיל
    -0.07
    קורס
    -0.06
    enic
    -0.06
     minecraft
    -0.06
    hour
    -0.06
    你自己
    -0.06
     indifferent
    -0.06
     surpassed
    -0.06
    POSITIVE LOGITS
    Impl
    0.07
    琅
    0.07
    Phone
    0.07
     annotate
    0.06
     appellant
    0.06
    主流
    0.06
    getDisplay
    0.06
    热销
    0.06
    (builder
    0.06
     QDialog
    0.06
    Activations Density 0.026%

    No Known Activations