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. 109965
    Prev
    Next
    INDEX
    Explanations

    transl

    np_max-act-logits · gemini-2.0-flash
    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
     sprayed
    -0.07
    _STATUS
    -0.07
    水域
    -0.07
     Saw
    -0.07
     GSL
    -0.07
     IMAGE
    -0.07
    asses
    -0.07
    _representation
    -0.07
     camper
    -0.07
    霎
    -0.07
    POSITIVE LOGITS
    ilmington
    0.07
    Question
    0.07
     }
    ↵
    ↵
    0.07
    ")]↵
    0.06
    TU
    0.06
    杀手
    0.06
    ثور
    0.06
    โอ
    0.06
    **↵↵
    0.06
    隆
    0.06
    Activations Density 0.000%

    No Known Activations