Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19-RESID-POST-AA
    6. 72509
    Prev
    Next
    INDEX
    Explanations

    @="

    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
    .chomp
    -0.07
    IDL
    -0.07
     propel
    -0.07
    🥨
    -0.07
     pomocą
    -0.07
     ל
    -0.07
     לל
    -0.07
     jóvenes
    -0.07
    iendo
    -0.07
    _launch
    -0.07
    POSITIVE LOGITS
     censor
    0.07
    /set
    0.07
     Certain
    0.07
    �
    0.07
    MES
    0.07
     Securities
    0.06
    _active
    0.06
     backstory
    0.06
    _CONTROLLER
    0.06
    _department
    0.06
    Activations Density 0.001%

    No Known Activations