INDEX

Explanations

0

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

brands

-0.28

het

-0.28

prime

-0.27

 prime

-0.26

onus

-0.25

 hand

-0.25

onia

-0.25

æľīæīĢ

-0.24

la

-0.24

æīĭä¸Ń

-0.24

POSITIVE LOGITS

 McCabe

0.28

 McGu

0.27

ritch

0.26

 Entries

0.25

æĺ¨æĻļ

0.25

åľ¨ä»Ĭå¹´

0.24

(volume

0.24

å¤ľæĻļ

0.24

åĬŁè¯¾

0.24

PFN

0.24

Activations Density 0.002%

0

No Comments

No Known Activations