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. 87798
    Prev
    Next
    INDEX
    Explanations

    Terminate, terminology

    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
     buc
    -0.08
     Gio
    -0.08
    ustain
    -0.08
     Cue
    -0.07
    Aff
    -0.07
    .Str
    -0.07
    Rank
    -0.07
     bais
    -0.07
     Paleo
    -0.07
    ☺
    -0.07
    POSITIVE LOGITS
     Manila
    0.08
     notorious
    0.08
     operations
    0.08
     невозможно
    0.07
     ни
    0.07
    至于
    0.07
    weise
    0.07
    architecture
    0.07
    commercial
    0.07
     terminology
    0.07
    Activations Density 0.016%

    No Known Activations