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. 16651
    Prev
    Next
    INDEX
    Explanations

    World Day

    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
    transform
    -0.07
     Lyft
    -0.07
     SHR
    -0.07
    流水
    -0.07
    imientos
    -0.07
     DOT
    -0.07
     возможно
    -0.07
     חייב
    -0.06
    Howard
    -0.06
    /OR
    -0.06
    POSITIVE LOGITS
    _based
    0.07
     ((*
    0.07
    峛
    0.07
    "]);↵
    0.07
    					↵
    0.07
     cooldown
    0.07
    _challenge
    0.07
    たくない
    0.07
    '];
    ↵
    0.07
     =$
    0.06
    Activations Density 0.058%

    No Known Activations