INDEX

Explanations

academic/legal texts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 exact

-0.82

exact

-0.67

 exactly

-0.66

 Exact

-0.65

Exact

-0.64

ç²¾ç¡®

-0.57

 Exactly

-0.56

ç¡®åĪĩ

-0.56

 precise

-0.54

 precisely

-0.54

POSITIVE LOGITS

æĢ§è´¨

0.39

 nature

0.35

nature

0.32

ÑĥÑī

0.28

Nature

0.28

ossa

0.27

æľ¬è´¨

0.27

 Nature

0.27

æģ¯

0.27

 meaning

0.26

Activations Density 0.001%

academic/legal texts

No Comments

No Known Activations