INDEX

Explanations

:

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

duk

-0.28

èĨ¨

-0.27

obot

-0.26

æįŁä¼¤

-0.25

IndexChanged

-0.25

agement

-0.25

iar

-0.25

åķĦ

-0.25

ä¿®å¤į

-0.25

é¦Ĩ

-0.24

POSITIVE LOGITS

ponential

0.26

 waived

0.25

ç²īä¸Ŀ

0.24

 former

0.24

 profiling

0.24

æ¯ĶåĪ©æĹ¶

0.23

((_

0.23

(({

0.23

posable

0.23

 evasion

0.23

Activations Density 0.846%

:

No Comments

No Known Activations