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. 41344
    Prev
    Next
    INDEX
    Explanations

    holography gravity

    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
     vile
    -0.07
     ],↵↵
    -0.07
    驾驭
    -0.07
    PILE
    -0.07
    콱
    -0.07
    	redirect
    -0.07
    .API
    -0.07
    锶
    -0.07
     compelling
    -0.07
    哪里
    -0.06
    POSITIVE LOGITS
     parentheses
    0.08
     ctxt
    0.08
     diagon
    0.07
     Children
    0.07
    茕
    0.07
    ocytes
    0.07
    톢
    0.07
    (ss
    0.07
     GW
    0.07
     groupe
    0.07
    Activations Density 0.020%

    No Known Activations