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. 11-RESID-POST-AA
    6. 41435
    Prev
    Next
    INDEX
    Explanations

    ($

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]<<
    -0.08
    疍
    -0.08
    geries
    -0.07
     ReactiveFormsModule
    -0.07
     ApiException
    -0.07
    史上最
    -0.07
    	Session
    -0.07
     altern
    -0.07
     Indiana
    -0.07
    Labour
    -0.07
    POSITIVE LOGITS
    .createClass
    0.07
     ($
    0.07
    /pkg
    0.07
    _DUMP
    0.07
    -special
    0.07
    صل
    0.07
    cı
    0.06
    -bold
    0.06
     everything
    0.06
    зер
    0.06
    Activations Density 0.007%

    No Known Activations