INDEX

Explanations

code/conversational fragments

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

\Migration

-0.28

 Mend

-0.27

ignment

-0.27

duy

-0.26

è¾«

-0.26

æįĨ

-0.25

icks

-0.25

tings

-0.25

 Kimber

-0.25

æīĢæľīäºº

-0.25

POSITIVE LOGITS

 needless

0.29

äº¬æ´¥

0.27

 addTarget

0.25

èķ¤

0.25

urnal

0.24

?v

0.24

 anyhow

0.24

ä¸Ģç«Ļ

0.24

 Ð²ÑĭÑĢÐ°Ð¶ÐµÐ½

0.24

å¾·æĭī

0.23

Activations Density 0.020%

code/conversational fragments

No Comments

No Known Activations