INDEX

Explanations

Complex grammatical structures

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

lius

-0.27

çĶ¨éĩı

-0.25

_singular

-0.25

singular

-0.24

çĲĥ

-0.24

umen

-0.24

 singular

-0.24

Any

-0.23

ä¼ģ

-0.23

éĻįæ¸©

-0.23

POSITIVE LOGITS

\Contracts

0.26

partials

0.26

åıįæŃ£

0.26

iare

0.24

 Turk

0.24

_Impl

0.24

ANTS

0.23

.define

0.23

fast

0.23

otte

0.23

Activations Density 0.004%

Complex grammatical structures

No Comments

No Known Activations