INDEX

Explanations

code snippets and data

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

ä¸ĢäºĽ

-0.28

things

-0.28

å¹´ç¬¬

-0.27

-mf

-0.26

åŃ¦æł¡çļĦ

-0.26

äºĽ

-0.25

uth

-0.25

 Lots

-0.25

å¤§éĩıçļĦ

-0.24

subplot

-0.24

POSITIVE LOGITS

ativity

0.28

inese

0.26

áº¡n

0.25

 plaintext

0.25

åĳ¨è½¬

0.25

èĦļæŃ¥

0.24

 latex

0.24

°

0.24

adal

0.24

 Walker

0.24

Activations Density 0.012%

code snippets and data

No Comments

No Known Activations