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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 1055
    Prev
    Next
    INDEX
    Explanations

    technical/scientific descriptions

    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
    _MAIN
    -0.07
    @Test
    -0.07
    	NULL
    -0.07
    Configurer
    -0.06
    YOU
    -0.06
    [right
    -0.06
    	exit
    -0.06
    @endsection
    -0.06
     ■
    -0.06
    これらの
    -0.06
    POSITIVE LOGITS
     replaces
    0.07
    pectral
    0.07
    iros
    0.07
    cy
    0.07
     Assass
    0.07
    뱡
    0.06
    财力
    0.06
     Dorothy
    0.06
     Says
    0.06
    开采
    0.06
    Activations Density 0.228%

    No Known Activations