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. 15-RESID-POST-AA
    6. 127907
    Prev
    Next
    INDEX
    Explanations

    making claims/arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unle
    -0.07
    "That
    -0.07
     Niet
    -0.07
    📔
    -0.06
    .normalize
    -0.06
    -method
    -0.06
     Winston
    -0.06
    (direction
    -0.06
    /'↵
    -0.06
    -purple
    -0.06
    POSITIVE LOGITS
    쌌
    0.08
    encoded
    0.08
     absorbing
    0.07
     regrets
    0.07
     RTE
    0.07
    少不了
    0.07
     걸
    0.07
    𒊑
    0.07
    -coded
    0.07
     ран
    0.07
    Activations Density 0.109%

    No Known Activations