INDEX

Explanations

code and names

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

otes

-0.30

ACLE

-0.28

ÐµÑĢÐ¶

-0.26

_lens

-0.26

OTES

-0.26

berry

-0.26

uters

-0.25

åī§æĥħ

-0.25

oten

-0.25

åķĨæľº

-0.25

POSITIVE LOGITS

 requestOptions

0.26

 structures

0.25

 sections

0.25

 Hipp

0.24

@section

0.24

éĶŃ

0.24

sections

0.24

 morph

0.23

"><?=

0.23

co

0.23

Activations Density 0.468%

code and names

No Comments

No Known Activations