INDEX

Explanations

water

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

thr

-0.27

 mold

-0.26

ernaut

-0.26

èĦ¾æ°Ķ

-0.26

æ¨¡

-0.25

PerPage

-0.25

_bindings

-0.25

ural

-0.24

 hoof

-0.24

è¯»æĩĤ

-0.24

POSITIVE LOGITS

elman

0.28

'.'

0.27

 ASAP

0.25

ä»¥åĨħ

0.25

æĴķ

0.25

åĲĦæł·

0.24

QC

0.24

éĴĪå¯¹æĢ§

0.24

è¡ĮæĶ¿éĥ¨éĹ¨

0.24

openh

0.23

Activations Density 0.148%

water

No Comments

No Known Activations