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. 16799
    Prev
    Next
    INDEX
    Explanations

    ā

    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
     Demon
    -0.09
     좋은
    -0.08
     한번
    -0.08
    前提是
    -0.08
    /pre
    -0.07
    fd
    -0.07
     разных
    -0.07
    _CLR
    -0.07
     просмотр
    -0.07
     Preference
    -0.07
    POSITIVE LOGITS
     ligne
    0.08
    _TEMP
    0.08
     Gew
    0.08
     peak
    0.08
    civil
    0.07
    nees
    0.07
    �
    0.07
    physical
    0.07
     https
    0.07
    Mass
    0.07
    Activations Density 0.026%

    No Known Activations