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. 88394
    Prev
    Next
    INDEX
    Explanations

    Scientific paper introductions

    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
     יום
    -0.07
     distint
    -0.07
    情�
    -0.07
    ulos
    -0.07
    aroo
    -0.07
     onChanged
    -0.07
     delve
    -0.07
    ⵣ
    -0.07
     TestUtils
    -0.07
     ocas
    -0.06
    POSITIVE LOGITS
    IP
    0.08
    ASH
    0.07
     "',
    0.07
    +="
    0.07
     EVENTS
    0.07
    ILING
    0.07
     CN
    0.07
     "<
    0.07
    ATION
    0.07
     CON
    0.07
    Activations Density 0.002%

    No Known Activations