INDEX

Explanations

know

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_25.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.25.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

entar

-0.28

entin

-0.26

 afford

-0.26

æĪĲä¸ºä¸ŃåĽ½

-0.26

entai

-0.25

ä¸ĥåįģ

-0.25

ç®¡çĲĨä½ĵç³»

-0.24

çī¹çĤ¹

-0.24

ldr

-0.24

alin

-0.24

POSITIVE LOGITS

.Done

0.29

XYZ

0.28

ä¸ĭæ¸¸

0.28

åĽ½å¤ĸ

0.27

YPE

0.27

åĲĪèµĦ

0.27

Wig

0.26

 ÐļÑĥ

0.26

scp

0.25

iam

0.25

Activations Density 0.027%

know

No Comments

No Known Activations