INDEX

Explanations

innitus

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

pins

-0.29

è´³

-0.28

çĮİ

-0.28

,map

-0.27

brew

-0.25

ogui

-0.25

pect

-0.25

atories

-0.24

agues

-0.24

WISE

-0.24

POSITIVE LOGITS

è¡¨çİ°

0.25

actus

0.24

 interv

0.24

Ø¨ÙĤ

0.24

èĮ«

0.24

 grade

0.23

vox

0.23

 comp

0.23

çĤ¹å¤´

0.23

avail

0.23

Activations Density 0.020%

innitus

No Comments

No Known Activations