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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 86212
    Prev
    Next
    INDEX
    Explanations

    assertion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    族自治县
    -0.08
     deleg
    -0.07
    招商引资
    -0.07
    .datasets
    -0.07
    gency
    -0.07
    <bool
    -0.07
    埇
    -0.07
    .addData
    -0.07
    能够让
    -0.07
     paralyzed
    -0.07
    POSITIVE LOGITS
     ");
    0.07
    �
    0.07
    �
    0.07
    	content
    0.07
     title
    0.07
    前
    0.07
    headline
    0.07
    时表示
    0.06
    	writer
    0.06
    📻
    0.06
    Activations Density 0.005%

    No Known Activations