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. 19-RESID-POST-AA
    6. 71900
    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
    堇
    -0.08
    罂
    -0.08
    drs
    -0.08
     lumin
    -0.07
     нич
    -0.07
     kaum
    -0.07
     dần
    -0.07
     банков
    -0.07
     số
    -0.07
    ije
    -0.07
    POSITIVE LOGITS
    ("<
    0.07
    (cart
    0.07
    .setContentType
    0.07
    Brightness
    0.07
    have
    0.07
    			  
    0.07
    適
    0.07
     taper
    0.07
    𬳵
    0.07
    kker
    0.06
    Activations Density 0.004%

    No Known Activations