Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 31362
    Prev
    Next
    INDEX
    Explanations

    may

    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
     dll
    -0.07
     northeastern
    -0.07
     ?>>
    -0.07
    .Audio
    -0.07
    >Nama
    -0.07
     Duration
    -0.07
    砠
    -0.07
    $errors
    -0.06
    .length
    -0.06
     MCS
    -0.06
    POSITIVE LOGITS
    _passed
    0.07
     Bradford
    0.07
     Brad
    0.07
     fragments
    0.07
    fol
    0.07
    _ut
    0.06
    .deploy
    0.06
    	total
    0.06
    链
    0.06
    heart
    0.06
    Activations Density 0.005%

    No Known Activations