INDEX

Explanations

Conversational forum posts

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

affles

-0.27

agner

-0.27

æ¶ĤæĬ¹

-0.27

èµ¤

-0.26

zet

-0.26

 accelerated

-0.25

åĳĬåĪ«

-0.25

 spins

-0.25

 distributed

-0.25

 acceler

-0.25

POSITIVE LOGITS

guard

0.28

edio

0.28

Healthy

0.26

YLE

0.25

 ctype

0.24

 bulk

0.24

 intuition

0.24

çªķ

0.24

ROL

0.24

ä¸ĢèĪ¬æĺ¯

0.23

Activations Density 0.011%

Conversational forum posts

No Comments

No Known Activations