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. 71234
    Prev
    Next
    INDEX
    Explanations

    Forum posts

    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
    投注
    -0.08
     {$
    -0.07
    NTSTATUS
    -0.07
     tasks
    -0.07
    .Flush
    -0.07
    游击
    -0.06
    Exchange
    -0.06
    TypeID
    -0.06
     dành
    -0.06
    场馆
    -0.06
    POSITIVE LOGITS
    "]
    ↵
    0.08
    咴
    0.07
    .od
    0.07
    메
    0.07
     עבודות
    0.07
    /;↵
    0.07
    _reply
    0.06
     Yellow
    0.06
    Helmet
    0.06
     ↵↵
    0.06
    Activations Density 0.213%

    No Known Activations