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. 24656
    Prev
    Next
    INDEX
    Explanations

    /bin

    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
    AXB
    -0.09
    .TextView
    -0.09
     Alps
    -0.07
    👦
    -0.07
     Andres
    -0.07
     sonrası
    -0.07
    �
    -0.07
    下半场
    -0.07
    _GC
    -0.07
    💳
    -0.07
    POSITIVE LOGITS
     goog
    0.08
    _EOL
    0.07
     COMMENT
    0.07
     seperate
    0.07
    Boolean
    0.07
    Fore
    0.07
     noe
    0.07
    衡水
    0.07
    𝇗
    0.06
     Human
    0.06
    Activations Density 0.004%

    No Known Activations