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. 16661
    Prev
    Next
    INDEX
    Explanations

    genus

    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
    ACING
    -0.07
    ס
    -0.07
     RENDER
    -0.07
     prescriptions
    -0.07
     +#+
    -0.07
     Psr
    -0.07
    차
    -0.07
    散发
    -0.07
     emphasizing
    -0.07
     capacità
    -0.07
    POSITIVE LOGITS
    公示
    0.07
    ⁿ
    0.07
     Fool
    0.07
     group
    0.07
    ゔ
    0.07
     wc
    0.07
    /y
    0.07
     NgModule
    0.06
     disclosures
    0.06
     Highlands
    0.06
    Activations Density 0.001%

    No Known Activations