© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 7592
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
     الشباب
    -0.07
    缣
    -0.07
    僮
    -0.07
    �
    -0.07
     objeto
    -0.06
     peque
    -0.06
    颐
    -0.06
     criança
    -0.06
     الطلاب
    -0.06
     enfermed
    -0.06
    POSITIVE LOGITS
     globals
    0.08
     mot
    0.08
    _SPI
    0.07
     morality
    0.07
     Datagram
    0.07
     moral
    0.07
     LM
    0.07
     mijn
    0.07
    三分
    0.07
    MOV
    0.07
    Activations Density 0.000%

    No Known Activations