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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2444
    Prev
    Next
    INDEX
    Explanations

    that

    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
     entirely
    -0.08
     Vin
    -0.08
     debated
    -0.07
     tube
    -0.07
    想过
    -0.07
    .bits
    -0.07
    -built
    -0.07
     ogłoszen
    -0.07
    \Middleware
    -0.06
    ustain
    -0.06
    POSITIVE LOGITS
    _TUN
    0.07
    (Session
    0.07
    (ver
    0.07
    𝗕
    0.07
     stripper
    0.07
    Prom
    0.07
    COMM
    0.06
    /W
    0.06
    目标
    0.06
    /form
    0.06
    Activations Density 0.040%

    No Known Activations