INDEX

Explanations

-omics

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

msp

-0.30

ms

-0.28

loses

-0.27

ms

-0.26

utters

-0.26

å·¥äºº

-0.26

à¹Ħà¸£

-0.25

è´½

-0.24

NECT

-0.24

prog

-0.24

POSITIVE LOGITS

(strict

0.27

éĺ³

0.27

Ey

0.27

DateString

0.27

 Ones

0.26

è§Ħ

0.24

 hopeful

0.24

åĿĳ

0.24

 deepen

0.24

-Feb

0.23

Activations Density 0.119%

-omics

No Comments

No Known Activations