INDEX

Explanations

adverbs

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

uts

-0.27

nen

-0.24

æ¢Ŀä»¶

-0.24

ÑĢÐ°Ð¶Ð°

-0.24

usher

-0.24

Powered

-0.24

ensively

-0.23

uting

-0.23

ìĬµ

-0.23

regation

-0.23

POSITIVE LOGITS

.true

0.28

geist

0.27

‘

0.27

ocities

0.27

 Fior

0.26

ibel

0.26

‘

0.26

äººæ°ĳæĹ¥æĬ¥

0.25

ï¼Į↵↵

0.25

 poles

0.24

Activations Density 0.001%

adverbs

No Comments

No Known Activations