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. 24371
    Prev
    Next
    INDEX
    Explanations

    say "-ly" words

    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
    梽
    -0.08
     undergo
    -0.08
    /sm
    -0.08
    すご
    -0.07
    疰
    -0.07
    _CSR
    -0.07
    	ZEPHIR
    -0.07
    ฮ
    -0.07
    毋
    -0.07
    تأك
    -0.07
    POSITIVE LOGITS
    (bucket
    0.07
     minim
    0.07
     READ
    0.06
     parms
    0.06
     Saving
    0.06
    平整
    0.06
    iances
    0.06
     null
    0.06
    getList
    0.06
    \<
    0.06
    Activations Density 0.037%

    No Known Activations