INDEX

Explanations

forests

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

#@

-0.29

æ´®

-0.27

sig

-0.26

.inject

-0.26

ä¹¡

-0.25

æ§½

-0.25

ext

-0.25

å½°

-0.24

#{@

-0.24

å£®

-0.24

POSITIVE LOGITS

æĿĤ

0.27

æĬ¤åį«

0.27

[number

0.25

å¤ĩæ¡Ī

0.25

 FormsModule

0.25

ices

0.25

tons

0.25

ayÄ±

0.25

kin

0.25

é¢Ĺ

0.24

Activations Density 0.410%

forests

No Comments

No Known Activations