INDEX

Explanations

reach

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

 Falk

-0.31

èĩ£

-0.27

errer

-0.27

 cruising

-0.26

èĩªæĦ¿

-0.26

å²ĳ

-0.26

ÙĬØ±

-0.25

urat

-0.25

 chuyáº¿n

-0.24

DebugEnabled

-0.24

POSITIVE LOGITS

 whence

0.28

bose

0.26

 snapshots

0.26

 presente

0.25

.boost

0.24

 bills

0.24

 continua

0.24

 roast

0.24

 recall

0.24

ymes

0.24

Activations Density 0.024%

reach

No Comments

No Known Activations