INDEX

Explanations

comparisons

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

ICA

-0.28

 Rather

-0.26

 oversh

-0.26

LOW

-0.25

èĢĮéĿŀ

-0.25

ACE

-0.25

 quot

-0.24

 Advantage

-0.24

plode

-0.24

æľīç§į

-0.24

POSITIVE LOGITS

ewire

0.27

çĲĨæĥ³

0.26

 hang

0.26

ä¹ĭæĺŁ

0.26

çļĦçĲĨæĥ³

0.25

ä¾Ŀæ³ķ

0.24

ANDING

0.24

æĪĳèĥ½

0.24

æħİéĩį

0.23

/mit

0.23

Activations Density 0.004%

comparisons

No Comments

No Known Activations