INDEX

Explanations

from

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

adir

-0.31

å¤ĩ

-0.27

csr

-0.26

iasi

-0.25

 spor

-0.24

spath

-0.24

 Spam

-0.23

_sp

-0.23

ea

-0.23

oley

-0.23

POSITIVE LOGITS

 interpreted

0.28

ä¹Ŀåįģ

0.25

ayo

0.24

Metro

0.24

interpreted

0.23

çļĦæĹ¶åĢĻ

0.23

agues

0.23

åŁºæķ°

0.23

.executeUpdate

0.23

Activations Density 0.016%

from

No Comments

No Known Activations