INDEX

Explanations

existential

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

 existing

-0.29

chemes

-0.26

ocks

-0.25

lements

-0.25

 Worst

-0.25

 worst

-0.25

inidad

-0.24

ÅĤuÅ¼

-0.24

 darker

-0.24

atement

-0.24

POSITIVE LOGITS

æĭ¾

0.27

çľģ

0.25

-native

0.25

ç²¾åĬĽ

0.25

bral

0.25

 jaws

0.25

é«ĺåľ°

0.24

çľģåħ¬å®īåİħ

0.24

åħ¨çľģ

0.24

clean

0.24

Activations Density 0.039%

existential

No Comments

No Known Activations