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. 11-RESID-POST-AA
    6. 1919
    Prev
    Next
    INDEX
    Explanations

    chemical storage

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Limited
    -0.07
    �
    -0.06
     Colts
    -0.06
    .rightBarButtonItem
    -0.06
    .gb
    -0.06
     [][]
    -0.06
    起伏
    -0.06
    .",
    ↵
    -0.06
     Equip
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    identifier
    0.09
    كن
    0.07
     Education
    0.07
     sie
    0.07
    _ids
    0.07
     język
    0.07
     anz
    0.07
    neas
    0.07
    	fi
    0.07
    _LANG
    0.07
    Activations Density 0.026%

    No Known Activations