© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    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. 126420
    Prev
    Next
    INDEX
    Explanations

    situated

    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
    ="(
    -0.08
    ".$
    -0.08
    ☓
    -0.07
     steal
    -0.07
    Xd
    -0.07
    	or
    -0.07
    ⏮
    -0.07
    挑战
    -0.07
    Extract
    -0.07
    _distances
    -0.07
    POSITIVE LOGITS
     situated
    0.09
    洫
    0.08
     jars
    0.07
     wc
    0.07
    半夜
    0.07
     compartment
    0.07
     goût
    0.07
     Pass
    0.07
     пут
    0.07
    年の
    0.06
    Activations Density 0.005%

    No Known Activations