INDEX

Explanations

helix

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

èº«

-0.30

æĹłæĦı

-0.27

æķ£

-0.27

ParameterValue

-0.27

zzo

-0.27

çĴ©

-0.26

amespace

-0.26

apol

-0.25

 Naturally

-0.25

zion

-0.24

POSITIVE LOGITS

Iv

0.32

æĬ¤

0.27

åĪĳäºĭ

0.26

 drinkers

0.26

.INPUT

0.25

airo

0.25

uya

0.25

é»ĳçĻ½

0.25

cr

0.24

IJ

0.24

Activations Density 0.006%

helix

No Comments

No Known Activations